webAI-Official commited on
Commit ·
9563ba7
0
Parent(s):
Publish TwIL-8B
Browse files- .gitattributes +44 -0
- LICENSE.md +36 -0
- README.md +381 -0
- TwIL-8B-F16-verbose.gguf +3 -0
- TwIL-8B-Q4_K_M-balanced.gguf +3 -0
- TwIL-8B-Q4_K_M-verbose.gguf +3 -0
- TwIL-8B-Q8_0-verbose.gguf +3 -0
- apache-2.0-LICENSE.txt +202 -0
- benchmarks.png +3 -0
- chat_template.jinja +184 -0
- config.json +34 -0
- generation_config.json +10 -0
- model-balanced.safetensors +3 -0
- model.safetensors.index.json +370 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- verbose/chat_template.jinja +184 -0
- verbose/config.json +34 -0
- verbose/generation_config.json +10 -0
- verbose/model-verbose.safetensors +3 -0
- verbose/model.safetensors.index.json +370 -0
- verbose/tokenizer.json +0 -0
- verbose/tokenizer_config.json +14 -0
.gitattributes
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
TwIL-8B-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
TwIL-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
TwIL-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
TwIL-8B-evaluation-report.pdf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
TwIL-8B-Q4_K_M-balanced.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
TwIL-8B-F16-verbose.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
TwIL-8B-Q8_0-verbose.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
TwIL-8B-Q4_K_M-verbose.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
benchmarks.png filter=lfs diff=lfs merge=lfs -text
|
LICENSE.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
webAI Non-Commercial License ver. 1.0
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
1. Definitions
|
| 5 |
+
|
| 6 |
+
“Licensor” means any person or entity that distributes its Work. “Work” means (a) the original work of authorship made available under this license, which may include software, documentation, or other files, and (b) any additions to or derivative works thereof that are made available under this license. The terms “reproduce,” “reproduction,” “derivative works,” and “distribution” have the meaning as provided under U.S. copyright law; provided, however, that for the purposes of this license, derivative works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work. Works are “made available” under this license by including in or with the Work either (a) a copyright notice referencing the applicability of this license to the Work, or (b) a copy of this license.
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
2. License Grant
|
| 10 |
+
|
| 11 |
+
2.1 Copyright Grant. Subject to the terms and conditions of this license, each Licensor grants to you a perpetual, worldwide, non-exclusive, royalty-free, copyright license to use, reproduce, prepare derivative works of, publicly display, publicly perform, sublicense and distribute its Work and any resulting derivative works in any form.
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
3. Limitations
|
| 15 |
+
|
| 16 |
+
3.1 Redistribution. You may reproduce or distribute the Work only if (a) you do so under this license, (b) you include a complete copy of this license with your distribution, and (c) you retain without modification any copyright, patent, trademark, or attribution notices that are present in the Work.
|
| 17 |
+
|
| 18 |
+
3.2 Derivative Works. You may specify that additional or different terms apply to the use, reproduction, and distribution of your derivative works of the Work (“Your Terms”) only if (a) Your Terms provide that the use limitation in Section 3.3 applies to your derivative works, and (b) you identify the specific derivative works that are subject to Your Terms. Notwithstanding Your Terms, this license (including the redistribution requirements in Section 3.1) will continue to apply to the Work itself.
|
| 19 |
+
|
| 20 |
+
3.3 Use Limitation. The Work and any derivative works thereof only may be used or intended for use non-commercially. As used herein, “non-commercially” means for non-commercial research and educational purposes only.
|
| 21 |
+
|
| 22 |
+
3.4 Patent Claims. If you bring or threaten to bring a patent claim against any Licensor (including any claim, cross-claim or counterclaim in a lawsuit) to enforce any patents that you allege are infringed by any Work, then your rights under this license from such Licensor (including the grant in Section 2.1) will terminate immediately.
|
| 23 |
+
|
| 24 |
+
3.5 Trademarks. This license does not grant any rights to use any Licensor's or its affiliates' names, logos, or trademarks, except as necessary to reproduce the notices described in this license. Nothing in this license shall be construed as permission to use the trade names, trademarks, service marks, or product names of webAI, Inc. or its affiliates to endorse, promote, or imply association with any derivative work, product, service, or entity, without prior written consent from webAI, Inc. Use of the Work does not imply endorsement by webAI, Inc. of any derivative work, product, service, or entity.
|
| 25 |
+
|
| 26 |
+
3.6 Termination. If you violate any term of this license, then your rights under this license (including the grant in Section 2.1) will terminate immediately.
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
4. Disclaimer of Warranty.
|
| 30 |
+
|
| 31 |
+
THE WORK IS PROVIDED “AS IS” WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OR CONDITIONS OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE OR NON-INFRINGEMENT. YOU BEAR THE RISK OF UNDERTAKING ANY ACTIVITIES UNDER THIS LICENSE.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
5. Limitation of Liability.
|
| 35 |
+
|
| 36 |
+
EXCEPT AS PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE SHALL ANY LICENSOR BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF OR RELATED TO THIS LICENSE, THE USE OR INABILITY TO USE THE WORK (INCLUDING BUT NOT LIMITED TO LOSS OF GOODWILL, BUSINESS INTERRUPTION, LOST PROFITS OR DATA, COMPUTER FAILURE OR MALFUNCTION, OR ANY OTHER DAMAGES OR LOSSES), EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
|
README.md
ADDED
|
@@ -0,0 +1,381 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
library_name: transformers
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
base_model: ibm-granite/granite-4.2-8b
|
| 7 |
+
license: other
|
| 8 |
+
license_name: webai-non-commercial-license-ver.-1.0
|
| 9 |
+
license_link: https://huggingface.co/webAI-Official/TwIL-8B/blob/main/LICENSE.md
|
| 10 |
+
tags:
|
| 11 |
+
- granite
|
| 12 |
+
- granite-4.2
|
| 13 |
+
- twil
|
| 14 |
+
- reasoning
|
| 15 |
+
- math
|
| 16 |
+
- code
|
| 17 |
+
- instruction-following
|
| 18 |
+
- reinforcement-learning
|
| 19 |
+
- grpo
|
| 20 |
+
- gguf
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# TwIL-8B
|
| 24 |
+
|
| 25 |
+
An 8.8B reasoning model for **math, code and instruction following**, post-trained from
|
| 26 |
+
[`ibm-granite/granite-4.2-8b`](https://huggingface.co/ibm-granite/granite-4.2-8b) with
|
| 27 |
+
full-parameter supervised fine-tuning and GRPO/DAPO reinforcement learning. It ships in two
|
| 28 |
+
variants that share one architecture and tokenizer: **balanced** (the default) and **verbose**.
|
| 29 |
+
See [Variants](#variants).
|
| 30 |
+
|
| 31 |
+
Against open models of similar size and up to 3.5x larger, TwIL-8B posts the highest MATH-500
|
| 32 |
+
(98.2) and LiveCodeBench (81.6 †) scores in the comparison and leads Qwen3.5-9B on IFBench
|
| 33 |
+
(+9.9 †). It is level with Qwen3.5-9B on contest math while using fewer tokens per problem. It
|
| 34 |
+
trails on knowledge-heavy benchmarks: GPQA Diamond, MMLU-Pro † and HLE †.
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
*TwIL-8B scores are for the balanced variant. † marks benchmarks measured on the verbose variant,
|
| 39 |
+
which have not yet been run on balanced. Competitor scores are published figures and were not
|
| 40 |
+
re-run; see [Evaluation protocol](#evaluation-protocol).*
|
| 41 |
+
|
| 42 |
+
## Highlights
|
| 43 |
+
|
| 44 |
+
* **Highest MATH-500 and AIME 2025 in the comparison.** MATH-500 98.2 against 96.6 for
|
| 45 |
+
Qwen3.5-9B and 87.9 for Gemma 4 31B; AIME 2025 88.3 against 87.1 for Gemma 4 31B.
|
| 46 |
+
* **Best LiveCodeBench in the group.** 81.6 † against 80.0 for Gemma 4 31B, 72.0 for Gemma 4 12B
|
| 47 |
+
and 65.6 for Qwen3.5-9B (+16.0). It is within 2.9–6.2 points of GPT-5.5, Claude Opus 4.8 and
|
| 48 |
+
Grok 4.3.
|
| 49 |
+
* **Strong instruction following.** IFBench 74.4 † is 9.9 points above Qwen3.5-9B, level with
|
| 50 |
+
Gemma 4 12B (74.0) and 1.6 behind Gemma 4 31B. It is also 12.2 points above Claude Opus 4.8
|
| 51 |
+
and 1.5 behind GPT-5.5. IFEval 91.8 is level with Qwen3.5-9B (91.5).
|
| 52 |
+
* **Level with Qwen3.5-9B on contest math, ahead of Gemma 4 12B.** Across the four contests both
|
| 53 |
+
publish, the averages are within 0.4 points. TwIL-8B leads on HMMT Nov 2025 (+3.8) and HMMT
|
| 54 |
+
Feb 2025 (+1.8) and trails on AIME 2026 (−4.2) and HMMT Feb 2026 (−3.0). On AIME 2026 it is
|
| 55 |
+
10.8 points above Gemma 4 12B and within 1 point of Gemma 4 31B.
|
| 56 |
+
* **Fewer tokens per problem.** About 19.5k output tokens per AIME 2026 problem against 31.2k
|
| 57 |
+
for Qwen3.5-9B (38% fewer), and 32.9k against 40.6k on HMMT Feb 2026 (19% fewer). It also
|
| 58 |
+
uses fewer tokens than Claude Opus 4.8 on AIME 2026 (21.0k), though at lower accuracy.
|
| 59 |
+
* **88–93% of the frontier on reasoning.** It reaches 93% of the best frontier score on
|
| 60 |
+
LiveCodeBench †, 92% on IFBench †, 90% on HMMT Nov 2025 and 88% on AIME 2026 and HMMT Feb 2025.
|
| 61 |
+
HMMT Feb 2026 is the exception, at 69%.
|
| 62 |
+
* **Runs locally.** 8.79B parameters in bf16 (16.38 GiB), with a 4.98 GiB Q4_K_M GGUF for CPU or
|
| 63 |
+
modest-VRAM GPUs.
|
| 64 |
+
|
| 65 |
+
It is **not** a knowledge model. GPQA Diamond (70.2) trails Qwen3.5-9B by 11.5 and Gemma 4 31B
|
| 66 |
+
by 14.1, and MMLU-Pro † and HLE † follow the same pattern. It also remains verbose next to the
|
| 67 |
+
frontier: GPT-5.5 solves AIME 2026 with about 5k tokens per problem. There is no safety or
|
| 68 |
+
preference tuning beyond what Granite 4.2 carries. See [Limitations](#limitations-and-caveats).
|
| 69 |
+
|
| 70 |
+
## Model Details
|
| 71 |
+
|
| 72 |
+
| Property | Value |
|
| 73 |
+
| --- | --- |
|
| 74 |
+
| Model ID | `webAI-Official/TwIL-8B` |
|
| 75 |
+
| Base model | [`ibm-granite/granite-4.2-8b`](https://huggingface.co/ibm-granite/granite-4.2-8b) |
|
| 76 |
+
| Total parameters | 8.79B (8,791,592,960) |
|
| 77 |
+
| Architecture | Granite decoder-only dense transformer (`GraniteForCausalLM`); 40 layers, hidden size 4096, 32 attention heads / 8 KV heads |
|
| 78 |
+
| Input / output | Text / text |
|
| 79 |
+
| Language | English |
|
| 80 |
+
| Tokenizer vocabulary size | 100,352 |
|
| 81 |
+
| Context window | 131,072 tokens (inherited from the base model) |
|
| 82 |
+
| Variants | `balanced` (default, repository root) and `verbose` (`verbose/` folder) |
|
| 83 |
+
| Checkpoint precision | bfloat16 (16.38 GiB per variant), plus GGUF builds |
|
| 84 |
+
| Post-training | Full-parameter SFT → GRPO/DAPO RL (verbose) → length-aware RL (balanced) |
|
| 85 |
+
| Reasoning format | Emits a `<think> … </think>` block before the answer (default chat template) |
|
| 86 |
+
| Evaluated decoding | High-effort pass@1, thinking enabled |
|
| 87 |
+
| Specialisation | Contest math, code and instruction following |
|
| 88 |
+
| License | webAI Non-Commercial License ver. 1.0 (base model: Apache License 2.0, IBM) |
|
| 89 |
+
|
| 90 |
+
### Variants
|
| 91 |
+
|
| 92 |
+
Both variants use the same architecture, tokenizer, chat template and generation config. They
|
| 93 |
+
differ only in how much they reason before answering.
|
| 94 |
+
|
| 95 |
+
| Variant | Safetensors | GGUF | Use it for |
|
| 96 |
+
| --- | --- | --- | --- |
|
| 97 |
+
| **balanced** (default) | `model-balanced.safetensors` (repository root) | `TwIL-8B-Q4_K_M-balanced.gguf` | General use. Shorter reasoning traces and a lower cost per answer. |
|
| 98 |
+
| **verbose** | `verbose/model-verbose.safetensors` | `TwIL-8B-F16-verbose.gguf`, `TwIL-8B-Q8_0-verbose.gguf`, `TwIL-8B-Q4_K_M-verbose.gguf` | Hard contest-style problems where accuracy matters more than token cost. Longer reasoning traces. |
|
| 99 |
+
|
| 100 |
+
`from_pretrained("webAI-Official/TwIL-8B")` loads **balanced**. Pass `subfolder="verbose"` to
|
| 101 |
+
load **verbose** (see [Usage](#usage)).
|
| 102 |
+
|
| 103 |
+
## Benchmarks
|
| 104 |
+
|
| 105 |
+
### Against open peers
|
| 106 |
+
|
| 107 |
+
| Benchmark | **TwIL-8B** (8.8B) | Qwen3.5-9B (9.7B) | Gemma 4 12B (12B) | Gemma 4 31B (31B) |
|
| 108 |
+
| --- | ---: | ---: | ---: | ---: |
|
| 109 |
+
| ***Math*** | | | | |
|
| 110 |
+
| MATH-500 | **98.2** | 96.6 | — | 87.9 |
|
| 111 |
+
| AIME 2025 | **88.3** | — | — | 87.1 |
|
| 112 |
+
| AIME 2026 | 88.3 | **92.5** | 77.5 | 89.2 |
|
| 113 |
+
| HMMT Feb 2025 | 85.0 | 83.2 | — | **88.7** |
|
| 114 |
+
| HMMT Feb 2026 | 68.2 | 71.2 | — | **77.2** |
|
| 115 |
+
| HMMT Nov 2025 | 86.7 | 82.9 | — | **87.5** |
|
| 116 |
+
| ***Science & knowledge*** | | | | |
|
| 117 |
+
| GPQA Diamond | 70.2 | 81.7 | 78.8 | **84.3** |
|
| 118 |
+
| MMLU-Pro † | 76.5 | 82.5 | 77.2 | **85.2** |
|
| 119 |
+
| HLE † | 12.6 | 14.9 | 5.2 | **19.5** |
|
| 120 |
+
| ***Instruction following*** | | | | |
|
| 121 |
+
| IFEval | 91.8 | 91.5 | 97.2 | **98.9** |
|
| 122 |
+
| IFBench † | 74.4 | 64.5 | 74.0 | **76.0** |
|
| 123 |
+
| ***Code*** | | | | |
|
| 124 |
+
| LiveCodeBench † | **81.6** | 65.6 | 72.0 | 80.0 |
|
| 125 |
+
| HumanEval † | 93.2 | 93.9 | — | **94.5** |
|
| 126 |
+
| HumanEval+ † | 88.3 | 87.2 | — | **91.5** |
|
| 127 |
+
| MBPP † | 93.7 | — | — | — |
|
| 128 |
+
| MBPP+ † | 79.1 | — | — | — |
|
| 129 |
+
| CRUXEval † | 97.1 | — | — | — |
|
| 130 |
+
|
| 131 |
+
† Measured on the verbose variant; not yet run on balanced. — means no published result could be
|
| 132 |
+
found. Bold marks the best score in each row where at least two models report one. All scores are
|
| 133 |
+
percentages.
|
| 134 |
+
|
| 135 |
+
TwIL-8B leads three rows outright (MATH-500, AIME 2025 and LiveCodeBench †). It is the strongest
|
| 136 |
+
model here at its own size on code and instruction following: against Qwen3.5-9B it is ahead on
|
| 137 |
+
LiveCodeBench † by 16.0 and IFBench † by 9.9, and the two are level on IFEval, HumanEval † and
|
| 138 |
+
HumanEval+ †. Contest math is close to even with Qwen3.5-9B (two contests each way), and ahead of
|
| 139 |
+
Gemma 4 12B by 10.8 on the one contest it publishes.
|
| 140 |
+
|
| 141 |
+
Gemma 4 31B, at about 3.5x the parameters, leads most remaining rows. TwIL-8B is ahead of it on
|
| 142 |
+
MATH-500, AIME 2025 and LiveCodeBench †, within one point on AIME 2026 and HMMT Nov 2025, and
|
| 143 |
+
behind on knowledge, instruction following and the hardest contest set (HMMT Feb 2026, −9.0).
|
| 144 |
+
MBPP †, MBPP+ † and CRUXEval † have no comparable published competitor numbers.
|
| 145 |
+
|
| 146 |
+
Notes on the competitor figures:
|
| 147 |
+
|
| 148 |
+
* Gemma 4 31B's HMMT scores were measured by the Qwen team (Qwen3.6-27B model card), not by Google.
|
| 149 |
+
Its MATH-500 (87.9) and AIME 2025 come from Red Hat's lighteval runs of the unquantized model;
|
| 150 |
+
the MATH-500 figure is unusually low and may reflect answer extraction.
|
| 151 |
+
* Google's IFEval figures for Gemma 4 (97.2 and 98.9) do not state the metric variant. Red Hat
|
| 152 |
+
measured 94.6 prompt-level strict for Gemma 4 31B.
|
| 153 |
+
* HumanEval and HumanEval+ comparators are community runs. The Gemma 4 31B run used a 512-token
|
| 154 |
+
cap, which leaves no room for thinking. The Qwen3.5-9B run had thinking enabled.
|
| 155 |
+
* Competitor LiveCodeBench scores are v6. Qwen3.5-9B's AIME 2026 and HMMT Feb 2026 scores are from
|
| 156 |
+
MathArena; its only public AIME 2025 results are non-thinking runs and are excluded.
|
| 157 |
+
|
| 158 |
+
### Against frontier models
|
| 159 |
+
|
| 160 |
+
GPT-5.5, Claude Opus 4.8 and Grok 4.3 at their highest published reasoning effort. The last column
|
| 161 |
+
is TwIL-8B's score as a share of the best frontier score on that row.
|
| 162 |
+
|
| 163 |
+
| Benchmark | **TwIL-8B** | GPT-5.5 (xhigh) | Claude Opus 4.8 (max) | Grok 4.3 (high) | Share of best frontier |
|
| 164 |
+
| --- | ---: | ---: | ---: | ---: | ---: |
|
| 165 |
+
| AIME 2026 | 88.3 | 100.0 | 100.0 | — | 88% |
|
| 166 |
+
| HMMT Feb 2025 | 85.0 | 96.5 | 96.5 | — | 88% |
|
| 167 |
+
| HMMT Feb 2026 | 68.2 | 98.5 | 95.5 | — | 69% |
|
| 168 |
+
| HMMT Nov 2025 | 86.7 | 96.5 | 96.5 | — | 90% |
|
| 169 |
+
| GPQA Diamond | 70.2 | 93.6 | 93.6 | 90.1 | 75% |
|
| 170 |
+
| MMLU-Pro † | 76.5 | 88.1 | 89.6 | 85.8 | 85% |
|
| 171 |
+
| HLE † | 12.6 | 45.8 | 48.7 | 37.2 | 26% |
|
| 172 |
+
| IFBench † | 74.4 | 75.9 | 62.2 | 81.3 | 92% |
|
| 173 |
+
| LiveCodeBench † | 81.6 | 85.3 | 87.8 | 84.5 | 93% |
|
| 174 |
+
|
| 175 |
+
TwIL-8B is closest to the frontier on **instruction following and code**. It beats Claude Opus 4.8
|
| 176 |
+
on IFBench † by 12.2 points and is within 2.9–6.2 points of all three models on LiveCodeBench †.
|
| 177 |
+
Contest math lands at 88–90% of the frontier, with HMMT Feb 2026, the hardest set, as the outlier
|
| 178 |
+
at 69%. **Knowledge is the largest gap**: GPQA Diamond trails by about 20–23 points and HLE † by 25–36.
|
| 179 |
+
These benchmarks reward stored knowledge, which tends to scale with parameter count more than with
|
| 180 |
+
reasoning-focused training.
|
| 181 |
+
|
| 182 |
+
These three are the most recent frontier releases with measured results on this benchmark set.
|
| 183 |
+
Newer releases (GPT-6.1 Sol, Claude Opus 5.5 and Grok 4.7) no longer report AIME, HMMT or GPQA.
|
| 184 |
+
Their only measured overlap is Artificial Analysis HLE: 52.9, 61.4 and 43.1 respectively.
|
| 185 |
+
|
| 186 |
+
### Head-to-head
|
| 187 |
+
|
| 188 |
+
Averages are taken only over benchmarks where both models have a score, so the benchmark count
|
| 189 |
+
differs by row and the averages are not comparable across rows.
|
| 190 |
+
|
| 191 |
+
| Opponent | Shared benchmarks | Wins–losses | Shared average (TwIL-8B vs opponent) | TwIL-8B leads on | TwIL-8B trails on |
|
| 192 |
+
| --- | ---: | :---: | :---: | --- | --- |
|
| 193 |
+
| Qwen3.5-9B | 13 | 7–6 | 78.1 vs 77.6 | LiveCodeBench † +16.0, IFBench † +9.9, HMMT Nov 2025 +3.8, HMMT Feb 2025 +1.8, MATH-500 +1.6 | GPQA Diamond −11.5, MMLU-Pro † −6.0, AIME 2026 −4.2, HMMT Feb 2026 −3.0 |
|
| 194 |
+
| Gemma 4 12B | 7 | 4–3 | 70.8 vs 68.8 | AIME 2026 +10.8, LiveCodeBench † +9.6, HLE † +7.4 | GPQA Diamond −8.6, IFEval −5.4 |
|
| 195 |
+
| Gemma 4 31B | 14 | 3–11 | 78.8 vs 82.0 | MATH-500 +10.3, LiveCodeBench † +1.6, AIME 2025 +1.2 | GPQA Diamond −14.1, HMMT Feb 2026 −9.0, MMLU-Pro † −8.7, IFEval −7.1 |
|
| 196 |
+
| GPT-5.5 | 9 | 0–9 | 71.5 vs 86.7 | — | HLE † −33.2, HMMT Feb 2026 −30.3, GPQA Diamond −23.4 |
|
| 197 |
+
| Claude Opus 4.8 | 9 | 1–8 | 71.5 vs 85.6 | IFBench † +12.2 | HLE † −36.1, HMMT Feb 2026 −27.3, GPQA Diamond −23.4 |
|
| 198 |
+
| Grok 4.3 | 5 | 0–5 | 63.1 vs 75.8 | — | HLE † −24.6, GPQA Diamond −19.9, MMLU-Pro † −9.3 |
|
| 199 |
+
|
| 200 |
+
### Tokens per problem
|
| 201 |
+
|
| 202 |
+
Mean output tokens per problem, with accuracy. Competitor figures are from MathArena; frontier
|
| 203 |
+
counts are rounded to the nearest 1k.
|
| 204 |
+
|
| 205 |
+
| Contest | **TwIL-8B** | Qwen3.5-9B | Claude Opus 4.8 | GPT-5.5 |
|
| 206 |
+
| --- | --- | --- | --- | --- |
|
| 207 |
+
| AIME 2026 | **19.5k** · 88.3% | 31.2k · 92.5% | 21.0k · 100.0% | 5.0k · 100.0% |
|
| 208 |
+
| HMMT Feb 2026 | **32.9k** · 68.2% | 40.6k · 71.2% | 30.0k · 95.5% | 8.0k · 98.5% |
|
| 209 |
+
|
| 210 |
+
Against Qwen3.5-9B, the closest open peer by size, TwIL-8B uses 38% fewer tokens on AIME 2026
|
| 211 |
+
and 19% fewer on HMMT Feb 2026, for 4.2 and 3.0 fewer points respectively. GPT-5.5 remains far
|
| 212 |
+
more token-efficient. Harnesses and tokenizers differ, so treat this comparison as directional.
|
| 213 |
+
|
| 214 |
+
## Usage
|
| 215 |
+
|
| 216 |
+
```python
|
| 217 |
+
import torch
|
| 218 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 219 |
+
|
| 220 |
+
model_id = "webAI-Official/TwIL-8B"
|
| 221 |
+
variant = None # balanced (default); use "verbose" for the verbose variant
|
| 222 |
+
|
| 223 |
+
tok = AutoTokenizer.from_pretrained(model_id, subfolder=variant or "")
|
| 224 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 225 |
+
model_id, subfolder=variant or "", dtype=torch.bfloat16, device_map="auto"
|
| 226 |
+
)
|
| 227 |
+
|
| 228 |
+
messages = [{"role": "user", "content":
|
| 229 |
+
"How many positive integers n < 1000 are divisible by 3 but not by 5? "
|
| 230 |
+
"Reason step by step, then give the final integer."}]
|
| 231 |
+
inputs = tok.apply_chat_template(
|
| 232 |
+
messages, add_generation_prompt=True,
|
| 233 |
+
return_tensors="pt", return_dict=True,
|
| 234 |
+
).to(model.device)
|
| 235 |
+
|
| 236 |
+
out = model.generate(**inputs, max_new_tokens=32768)
|
| 237 |
+
print(tok.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
|
| 238 |
+
```
|
| 239 |
+
|
| 240 |
+
Use a Transformers release with Granite 4.2 support. `return_dict=True` matters on Transformers
|
| 241 |
+
5.x, where `apply_chat_template` returns a `BatchEncoding` rather than a bare tensor.
|
| 242 |
+
|
| 243 |
+
The chat template opens a `<think>` block by default, so the model reasons before it answers.
|
| 244 |
+
Give it a large generation budget: on contest math, balanced averages about 19.5k tokens per AIME
|
| 245 |
+
2026 problem and 33k per HMMT Feb 2026 problem, and verbose writes more. A short budget truncates
|
| 246 |
+
the reasoning and scores far worse. The shipped `generation_config.json` samples with
|
| 247 |
+
`temperature=1.0` and `top_p=0.95`. The template also accepts `enable_thinking=False` and
|
| 248 |
+
`reasoning_effort="low"` through `chat_template_kwargs`. Both lower latency, but low-effort runs
|
| 249 |
+
score substantially lower and none of the numbers on this card use them.
|
| 250 |
+
|
| 251 |
+
To download a single variant:
|
| 252 |
+
|
| 253 |
+
```bash
|
| 254 |
+
# balanced
|
| 255 |
+
hf download webAI-Official/TwIL-8B --exclude "verbose/*" --exclude "*.gguf" --local-dir TwIL-8B-balanced
|
| 256 |
+
# verbose
|
| 257 |
+
hf download webAI-Official/TwIL-8B --include "verbose/*" --local-dir TwIL-8B
|
| 258 |
+
```
|
| 259 |
+
|
| 260 |
+
### GGUF / llama.cpp
|
| 261 |
+
|
| 262 |
+
| File | Variant | Quant | Size |
|
| 263 |
+
| --- | --- | --- | --- |
|
| 264 |
+
| `TwIL-8B-Q4_K_M-balanced.gguf` | balanced | Q4_K_M (importance matrix) | 4.98 GiB |
|
| 265 |
+
| `TwIL-8B-Q4_K_M-verbose.gguf` | verbose | Q4_K_M | 4.98 GiB |
|
| 266 |
+
| `TwIL-8B-Q8_0-verbose.gguf` | verbose | Q8_0 | 8.70 GiB |
|
| 267 |
+
| `TwIL-8B-F16-verbose.gguf` | verbose | F16 | 16.38 GiB |
|
| 268 |
+
|
| 269 |
+
```bash
|
| 270 |
+
llama-cli -hf webAI-Official/TwIL-8B --hf-file TwIL-8B-Q4_K_M-balanced.gguf -cnv -c 40960 -n 32768
|
| 271 |
+
```
|
| 272 |
+
|
| 273 |
+
Name the file with `--hf-file`, because each quant exists for more than one variant. Keep the
|
| 274 |
+
context and generation budget large for the same reason as above. The model uses a ChatML-style
|
| 275 |
+
template with `<|im_end|>` as EOS. All scores on this card were measured on the bf16 weights,
|
| 276 |
+
not on the GGUF builds, so expect small deviations, most likely at Q4_K_M.
|
| 277 |
+
|
| 278 |
+
## How it was built
|
| 279 |
+
|
| 280 |
+
1. **Supervised fine-tuning.** Full-parameter SFT of `ibm-granite/granite-4.2-8b` on reasoning
|
| 281 |
+
traces covering math, STEM and instruction following.
|
| 282 |
+
2. **Reinforcement learning.** GRPO/DAPO RL on math, code, STEM and instruction-following
|
| 283 |
+
prompts. This produces the **verbose** variant.
|
| 284 |
+
3. **Length-aware RL.** A further RL stage with a length-aware reward that favours shorter
|
| 285 |
+
reasoning traces, measured against per-domain length references for math, code, STEM and
|
| 286 |
+
instruction following. This produces the **balanced** variant.
|
| 287 |
+
|
| 288 |
+
The math, STEM and instruction-following training pools were decontaminated with 13-gram matching
|
| 289 |
+
against AIME (2025, 2026 and earlier years), HMMT Feb 2025 and Feb 2026, MATH-500, GPQA Diamond,
|
| 290 |
+
MMLU-Pro, HLE, IFEval, IFBench and LiveCodeBench. Both variants ship as full merged models, not
|
| 291 |
+
LoRA adapters.
|
| 292 |
+
|
| 293 |
+
## Limitations and caveats
|
| 294 |
+
|
| 295 |
+
* **Knowledge.** GPQA Diamond, MMLU-Pro † and HLE † trail larger open models and the frontier by
|
| 296 |
+
wide margins.
|
| 297 |
+
* **Coverage.** Rows marked † were measured on the verbose variant and have not yet been run on
|
| 298 |
+
balanced. SWE-bench, SuperGPQA, tool use and agentic tasks were not evaluated.
|
| 299 |
+
* **Cross-harness comparisons.** Competitor numbers come from each vendor's model card or from
|
| 300 |
+
third-party evaluations, with their own prompts, sampling and token budgets. The AIME and HMMT
|
| 301 |
+
sets have 30–33 problems, so one problem is worth about 3 points and gaps of that size are
|
| 302 |
+
within noise.
|
| 303 |
+
* **HLE scoring.** TwIL-8B's HLE uses a multiple-choice scoring rule. Competitor HLE scores are
|
| 304 |
+
text-only and judge-graded, so that comparison is approximate.
|
| 305 |
+
* **LiveCodeBench version.** Competitor scores are v6. The version and date window of TwIL-8B's
|
| 306 |
+
run are not recorded, so confirm them before quoting that gap.
|
| 307 |
+
* **Contamination.** HMMT Nov 2025 and the HumanEval, MBPP and CRUXEval suites were not in the
|
| 308 |
+
decontamination set, and decontamination of the code training data is not recorded.
|
| 309 |
+
* **Token cost.** Even balanced spends about 19.5k tokens per AIME 2026 problem, roughly 4x
|
| 310 |
+
GPT-5.5.
|
| 311 |
+
* **Not a general assistant.** There is no additional safety, preference or tool-use training
|
| 312 |
+
beyond what Granite 4.2 carries.
|
| 313 |
+
|
| 314 |
+
## Evaluation protocol
|
| 315 |
+
|
| 316 |
+
* **TwIL-8B:** internal high-effort pass@1 with thinking enabled, on the same harness for every
|
| 317 |
+
benchmark and both variants. Scores are shown as percentages (0.982 → 98.2).
|
| 318 |
+
* **Competitors:** reproduced from the public sources below, accessed 3 November 2026. No
|
| 319 |
+
competitor benchmark was re-run. Frontier models are at their highest published reasoning
|
| 320 |
+
effort. Model-predicted estimates on aggregator sites are excluded.
|
| 321 |
+
* **Naming:** "GPQA" means GPQA Diamond. AIME 2025 and AIME 2026 are the single-year sets.
|
| 322 |
+
|
| 323 |
+
## Relationship to TwIL-LM
|
| 324 |
+
|
| 325 |
+
TwIL-8B belongs to the same webAI TwIL family as
|
| 326 |
+
[TwIL-LM3](https://huggingface.co/webAI-Official/TwIL-LM3) and
|
| 327 |
+
[TwIL-LM3-Pro](https://huggingface.co/webAI-Official/TwIL-LM3-Pro). Those are 3B formal-logic
|
| 328 |
+
models; TwIL-8B targets contest math, code and instruction following at 8B, on IBM's Granite 4.2
|
| 329 |
+
8B base. Like them, it ships as a full model on `main`, loaded directly with
|
| 330 |
+
`AutoModelForCausalLM`.
|
| 331 |
+
|
| 332 |
+
## License and attribution
|
| 333 |
+
|
| 334 |
+
Released under the **webAI Non-Commercial License ver. 1.0**; see `LICENSE.md` in this repository.
|
| 335 |
+
|
| 336 |
+
The base model, [`ibm-granite/granite-4.2-8b`](https://huggingface.co/ibm-granite/granite-4.2-8b),
|
| 337 |
+
is Copyright IBM Corporation and is distributed under the Apache License 2.0; its license text is
|
| 338 |
+
retained as `apache-2.0-LICENSE.txt` and all credit for the base model goes to IBM. Apache 2.0
|
| 339 |
+
permits distributing derivative works under different terms provided attribution is preserved,
|
| 340 |
+
which is what the pair of license files in this repository does.
|
| 341 |
+
|
| 342 |
+
## Sources
|
| 343 |
+
|
| 344 |
+
Competitor figures on this card come from:
|
| 345 |
+
|
| 346 |
+
* [Gemma 4 model card](https://ai.google.dev/gemma/docs/core/model_card_4) (Google, thinking mode):
|
| 347 |
+
Gemma 4 12B and 31B AIME 2026, GPQA Diamond, MMLU-Pro, HLE and LiveCodeBench v6.
|
| 348 |
+
* [Gemma 4 Technical Report, Table 5](https://arxiv.org/abs/2607.02770): Gemma 4 IFEval and IFBench.
|
| 349 |
+
* [Qwen3.6-27B model card](https://huggingface.co/Qwen/Qwen3.6-27B), Gemma4-31B baseline column:
|
| 350 |
+
Gemma 4 31B HMMT Feb 2025, Nov 2025 and Feb 2026.
|
| 351 |
+
* [RedHatAI/gemma-4-31B-it-FP8-dynamic](https://huggingface.co/RedHatAI/gemma-4-31B-it-FP8-dynamic),
|
| 352 |
+
BF16 baseline: Gemma 4 31B MATH-500 and AIME 2025.
|
| 353 |
+
* [EvalPlus submission #300](https://github.com/evalplus/evalplus/issues/300): Gemma 4 31B HumanEval
|
| 354 |
+
and HumanEval+.
|
| 355 |
+
* [Qwen3.5-9B model card](https://huggingface.co/Qwen/Qwen3.5-9B) (thinking mode): GPQA Diamond,
|
| 356 |
+
MMLU-Pro, IFEval, IFBench, HMMT Feb 2025, HMMT Nov 2025 and LiveCodeBench v6.
|
| 357 |
+
* [MathArena, Qwen3.5-9B](https://matharena.ai/models/qwen_qwen3_5_9b): AIME 2026 and HMMT Feb 2026
|
| 358 |
+
accuracy and tokens per problem.
|
| 359 |
+
* [SOTA2 MATH-500 leaderboard](https://www.sota2.com/research/sota/math-on-math-500-score):
|
| 360 |
+
Qwen3.5-9B MATH-500.
|
| 361 |
+
* [Artificial Analysis via OpenRouter, Qwen3.5 9B](https://openrouter.ai/qwen/qwen3.5-9b:batch):
|
| 362 |
+
Qwen3.5-9B HLE.
|
| 363 |
+
* [nivvis/Qwen3.5-9B-EQ-v5.1](https://huggingface.co/nivvis/Qwen3.5-9B-EQ-v5.1-GGUF), vanilla
|
| 364 |
+
baseline row: Qwen3.5-9B HumanEval and HumanEval+.
|
| 365 |
+
* [Introducing GPT-5.5](https://openai.com/index/introducing-gpt-5-5/) and the
|
| 366 |
+
[Claude Opus 4.8 System Card](https://www.anthropic.com/claude-opus-4-8-system-card): GPQA Diamond.
|
| 367 |
+
* MathArena via [BenchLeader AIME 2026](https://www.benchleader.com/benchmarks/matharena_aime_2026),
|
| 368 |
+
[BenchLeader HMMT Feb 2026](https://www.benchleader.com/benchmarks/matharena_hmmt_feb_2026) and
|
| 369 |
+
[The Aggregate HMMT Feb 2025](https://theaggregate.ai/benchmark?slug=matharena-hmmt-feb-2025):
|
| 370 |
+
GPT-5.5 and Claude Opus 4.8 contest accuracy and tokens per problem.
|
| 371 |
+
* [GLM-5.2 model card](https://huggingface.co/zai-org/GLM-5.2): GPT-5.5 and Claude Opus 4.8 HMMT
|
| 372 |
+
Nov 2025.
|
| 373 |
+
* benchgap.net for [GPT-5.5](https://benchgap.net/model/gpt-5-5),
|
| 374 |
+
[Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8) and
|
| 375 |
+
[Grok 4.3](https://benchgap.net/model/grok-4-3) (measured rows only): Artificial Analysis HLE and
|
| 376 |
+
IFBench, and Vals AI MMLU-Pro and LiveCodeBench.
|
| 377 |
+
* [Artificial Analysis via OpenRouter, Grok 4.3](https://openrouter.ai/x-ai/grok-4.3): Grok 4.3
|
| 378 |
+
GPQA Diamond, HLE and IFBench.
|
| 379 |
+
* benchgap.net for the newest frontier releases, [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol),
|
| 380 |
+
[Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5) and
|
| 381 |
+
[Grok 4.7](https://benchgap.net/model/grok-4-7): Artificial Analysis HLE.
|
TwIL-8B-F16-verbose.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5d8f7d35d82c38e845f23612513ac49333e5fa23a1788d843449124e13b64bd
|
| 3 |
+
size 17587420608
|
TwIL-8B-Q4_K_M-balanced.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17bda82d2608ca61b6aca48394f212349ef1515d0d9a2e6edee06619152faa0e
|
| 3 |
+
size 5347917568
|
TwIL-8B-Q4_K_M-verbose.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5646abbb98f6ab81cfb9f7590aef894011ba50a259fb5d5aac8284d154e64ef0
|
| 3 |
+
size 5347917248
|
TwIL-8B-Q8_0-verbose.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6242f84e5d9854ca54a9f39dd14dadbd9eaad5b3d2bc6195d408cae69e8f85d6
|
| 3 |
+
size 9345613248
|
apache-2.0-LICENSE.txt
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
|
| 190 |
+
Copyright [yyyy] [name of copyright owner]
|
| 191 |
+
|
| 192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 193 |
+
you may not use this file except in compliance with the License.
|
| 194 |
+
You may obtain a copy of the License at
|
| 195 |
+
|
| 196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 197 |
+
|
| 198 |
+
Unless required by applicable law or agreed to in writing, software
|
| 199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 201 |
+
See the License for the specific language governing permissions and
|
| 202 |
+
limitations under the License.
|
benchmarks.png
ADDED
|
Git LFS Details
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- macro tool_to_json(tool) -%}
|
| 2 |
+
{%- set ns_tool = namespace(first=true) -%}
|
| 3 |
+
{{- '{' -}}
|
| 4 |
+
{%- for k, v in tool.items() -%}
|
| 5 |
+
{%- if k != 'defer_loading' and k != 'strict' -%}
|
| 6 |
+
{%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
|
| 7 |
+
{%- set ns_tool.first = false -%}
|
| 8 |
+
{{- '"' ~ k ~ '": ' ~ (v | tojson(ensure_ascii=False)) -}}
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- endfor -%}
|
| 11 |
+
{{- '}' -}}
|
| 12 |
+
{%- endmacro -%}
|
| 13 |
+
{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
|
| 14 |
+
{%- set low_effort = low_effort if low_effort is defined else False %}
|
| 15 |
+
{%- if reasoning_effort is defined and reasoning_effort is not none %}
|
| 16 |
+
{%- set low_effort = reasoning_effort == "low" %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
|
| 19 |
+
|
| 20 |
+
{%- set ns = namespace(last_user_idx = -1) %}
|
| 21 |
+
{%- set loop_messages = messages %}
|
| 22 |
+
{%- for m in loop_messages %}
|
| 23 |
+
{%- if m["role"] == "user" %}
|
| 24 |
+
{%- set ns.last_user_idx = loop.index0 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- endfor %}
|
| 27 |
+
|
| 28 |
+
{%- if messages[0]["role"] == "system" %}
|
| 29 |
+
{%- set system_message = messages[0]["content"] %}
|
| 30 |
+
{%- set loop_messages = messages[1:] %}
|
| 31 |
+
{%- else %}
|
| 32 |
+
{%- set system_message = "" %}
|
| 33 |
+
{%- set loop_messages = messages %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- if not tools is defined %}
|
| 36 |
+
{%- set tools = [] %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{# Recompute last_user_idx relative to loop_messages after handling system #}
|
| 39 |
+
{%- set ns = namespace(last_user_idx = -1) %}
|
| 40 |
+
{%- for m in loop_messages %}
|
| 41 |
+
{%- if m["role"] == "user" %}
|
| 42 |
+
{%- set ns.last_user_idx = loop.index0 %}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- if system_message is defined %}
|
| 46 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 47 |
+
{%- else %}
|
| 48 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 49 |
+
{{- "<|im_start|>system\n" }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 53 |
+
{%- if system_message is defined and system_message | length > 0 %}
|
| 54 |
+
{{- "\n\n" }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 57 |
+
{{- "<tools>" }}
|
| 58 |
+
{%- for tool in tools %}
|
| 59 |
+
{%- if tool.function is defined %}
|
| 60 |
+
{%- set tool = tool.function %}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- if tool.defer_loading is not defined or not tool.defer_loading %}
|
| 63 |
+
{{- '\n' ~ tool_to_json(tool) }}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{{- "\n</tools>" }}
|
| 67 |
+
|
| 68 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
{%- if system_message is defined %}
|
| 73 |
+
{{- '<|im_end|>\n' }}
|
| 74 |
+
{%- else %}
|
| 75 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
|
| 80 |
+
{%- for message in loop_messages %}
|
| 81 |
+
{%- if message.role == "assistant" %}
|
| 82 |
+
{# Add reasoning content in to content field for unified processing below. #}
|
| 83 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
|
| 84 |
+
{%- set content = "<think>\n" ~ message.reasoning_content ~ "\n</think>\n" ~ (message.content | default('', true)) %}
|
| 85 |
+
{%- else %}
|
| 86 |
+
{%- set content = message.content | default('', true) %}
|
| 87 |
+
{%- if content is string -%}
|
| 88 |
+
{# Allow downstream logic to to take care of broken thought, only handle coherent reasoning here. #}
|
| 89 |
+
{%- if '<think>' not in content and '</think>' not in content -%}
|
| 90 |
+
{%- set content = "<think></think>" ~ content -%}
|
| 91 |
+
{%- endif -%}
|
| 92 |
+
{%- else -%}
|
| 93 |
+
{%- set content = content -%}
|
| 94 |
+
{%- endif -%}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 97 |
+
{# Assistant message has tool calls. #}
|
| 98 |
+
{{- '<|im_start|>assistant\n' }}
|
| 99 |
+
{%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
|
| 100 |
+
{%- if content is string and content | trim | length > 0 %}
|
| 101 |
+
{%- if include_content %}
|
| 102 |
+
{{- (content | trim) ~ '\n' -}}
|
| 103 |
+
{%- else %}
|
| 104 |
+
{%- set c = (content | string) %}
|
| 105 |
+
{%- if '</think>' in c %}
|
| 106 |
+
{# Keep only content after the last closing think. Also generation prompt causes this. #}
|
| 107 |
+
{%- set c = c.split('</think>')[-1] %}
|
| 108 |
+
{%- elif '<think>' in c %}
|
| 109 |
+
{# If <think> was opened but never closed, drop the trailing think segment #}
|
| 110 |
+
{%- set c = c.split('<think>')[0] %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{%- set c = "<think></think>" ~ c | trim %}
|
| 113 |
+
{%- if c | length > 0 %}
|
| 114 |
+
{{- c ~ '\n' -}}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- else %}
|
| 118 |
+
{{- "<think></think>" -}}
|
| 119 |
+
{%- endif %}
|
| 120 |
+
{%- for tool_call in message.tool_calls %}
|
| 121 |
+
{%- if tool_call.function is defined %}
|
| 122 |
+
{%- set tool_call = tool_call.function %}
|
| 123 |
+
{%- endif %}
|
| 124 |
+
{{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
|
| 125 |
+
{%- if tool_call.arguments is defined %}
|
| 126 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 127 |
+
{{- '<parameter=' ~ args_name ~ '>\n' -}}
|
| 128 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 129 |
+
{{- args_value ~ '\n</parameter>\n' -}}
|
| 130 |
+
{%- endfor %}
|
| 131 |
+
{%- endif %}
|
| 132 |
+
{{- '</function>\n</tool_call>\n' -}}
|
| 133 |
+
{%- endfor %}
|
| 134 |
+
{{- '<|im_end|>\n' }}
|
| 135 |
+
{%- else %}
|
| 136 |
+
{# Assistant message doesn't have tool calls. #}
|
| 137 |
+
{%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
|
| 138 |
+
{{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
|
| 139 |
+
{%- else %}
|
| 140 |
+
{%- set c = (content | default('', true) | string) %}
|
| 141 |
+
{%- if '<think>' in c and '</think>' in c %}
|
| 142 |
+
{%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
|
| 143 |
+
{%- endif %}
|
| 144 |
+
{%- set c = c | trim %}
|
| 145 |
+
{%- if c | length > 0 %}
|
| 146 |
+
{{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
|
| 147 |
+
{%- else %}
|
| 148 |
+
{{- '<|im_start|>assistant\n<|im_end|>\n' }}
|
| 149 |
+
{%- endif %}
|
| 150 |
+
{%- endif %}
|
| 151 |
+
{%- endif %}
|
| 152 |
+
{%- elif message.role == "user" or message.role == "system" %}
|
| 153 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 154 |
+
{%- set content = message.content | string %}
|
| 155 |
+
{%- if message.role == "user" and loop.index0 == ns.last_user_idx and low_effort %}
|
| 156 |
+
{{- content + '\n\n{reasoning effort: low}' }}
|
| 157 |
+
{%- else %}
|
| 158 |
+
{{- content }}
|
| 159 |
+
{%- endif %}
|
| 160 |
+
{{- '<|im_end|>\n' }}
|
| 161 |
+
{%- elif message.role == "tool" %}
|
| 162 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 163 |
+
{{- '<|im_start|>user\n' }}
|
| 164 |
+
{%- endif %}
|
| 165 |
+
{{- '<tool_response>\n' }}
|
| 166 |
+
{{- message.content }}
|
| 167 |
+
{{- '\n</tool_response>\n' }}
|
| 168 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 169 |
+
{{- '<|im_end|>\n' }}
|
| 170 |
+
{%- elif loop.last %}
|
| 171 |
+
{{- '<|im_end|>\n' }}
|
| 172 |
+
{%- endif %}
|
| 173 |
+
{%- else %}
|
| 174 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 175 |
+
{%- endif %}
|
| 176 |
+
{%- endfor %}
|
| 177 |
+
|
| 178 |
+
{%- if add_generation_prompt %}
|
| 179 |
+
{%- if enable_thinking %}
|
| 180 |
+
{{- '<|im_start|>assistant\n<think>\n' }}
|
| 181 |
+
{%- else %}
|
| 182 |
+
{{- '<|im_start|>assistant\n<think></think>' }}
|
| 183 |
+
{%- endif %}
|
| 184 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 100283,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"embedding_multiplier": 1.0,
|
| 11 |
+
"eos_token_id": 100257,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 4096,
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 12800,
|
| 16 |
+
"logits_scaling": 1.0,
|
| 17 |
+
"max_position_embeddings": 131072,
|
| 18 |
+
"mlp_bias": false,
|
| 19 |
+
"model_type": "granite",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 40,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"pad_token_id": 100257,
|
| 24 |
+
"residual_multiplier": 1.0,
|
| 25 |
+
"rms_norm_eps": 1e-05,
|
| 26 |
+
"rope_parameters": {
|
| 27 |
+
"rope_theta": 10000000,
|
| 28 |
+
"rope_type": "default"
|
| 29 |
+
},
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"transformers_version": "5.5.3",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 100352
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100283,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 100257,
|
| 6 |
+
"pad_token_id": 100257,
|
| 7 |
+
"temperature": 1.0,
|
| 8 |
+
"top_p": 0.95,
|
| 9 |
+
"transformers_version": "5.5.3"
|
| 10 |
+
}
|
model-balanced.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79fe4b7e42b45d15f43c10e1e2fa0602409bcc8cad03911aa0d8c4a0846e3532
|
| 3 |
+
size 17583228544
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 17583185920
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-balanced.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-balanced.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-balanced.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-balanced.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-balanced.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-balanced.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-balanced.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-balanced.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-balanced.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-balanced.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-balanced.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-balanced.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-balanced.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-balanced.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-balanced.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-balanced.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-balanced.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-balanced.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-balanced.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-balanced.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-balanced.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-balanced.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-balanced.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-balanced.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-balanced.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-balanced.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-balanced.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-balanced.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 242 |
+
"model.layers.32.input_layernorm.weight": "model-balanced.safetensors",
|
| 243 |
+
"model.layers.32.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 245 |
+
"model.layers.32.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 251 |
+
"model.layers.33.input_layernorm.weight": "model-balanced.safetensors",
|
| 252 |
+
"model.layers.33.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 254 |
+
"model.layers.33.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 260 |
+
"model.layers.34.input_layernorm.weight": "model-balanced.safetensors",
|
| 261 |
+
"model.layers.34.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 263 |
+
"model.layers.34.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 269 |
+
"model.layers.35.input_layernorm.weight": "model-balanced.safetensors",
|
| 270 |
+
"model.layers.35.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 272 |
+
"model.layers.35.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 278 |
+
"model.layers.36.input_layernorm.weight": "model-balanced.safetensors",
|
| 279 |
+
"model.layers.36.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 281 |
+
"model.layers.36.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 287 |
+
"model.layers.37.input_layernorm.weight": "model-balanced.safetensors",
|
| 288 |
+
"model.layers.37.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 290 |
+
"model.layers.37.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 296 |
+
"model.layers.38.input_layernorm.weight": "model-balanced.safetensors",
|
| 297 |
+
"model.layers.38.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 299 |
+
"model.layers.38.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 305 |
+
"model.layers.39.input_layernorm.weight": "model-balanced.safetensors",
|
| 306 |
+
"model.layers.39.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 308 |
+
"model.layers.39.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 314 |
+
"model.layers.4.input_layernorm.weight": "model-balanced.safetensors",
|
| 315 |
+
"model.layers.4.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 317 |
+
"model.layers.4.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 323 |
+
"model.layers.5.input_layernorm.weight": "model-balanced.safetensors",
|
| 324 |
+
"model.layers.5.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 325 |
+
"model.layers.5.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 326 |
+
"model.layers.5.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 327 |
+
"model.layers.5.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 328 |
+
"model.layers.5.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 329 |
+
"model.layers.5.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 330 |
+
"model.layers.5.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 331 |
+
"model.layers.5.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 332 |
+
"model.layers.6.input_layernorm.weight": "model-balanced.safetensors",
|
| 333 |
+
"model.layers.6.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 334 |
+
"model.layers.6.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 335 |
+
"model.layers.6.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 336 |
+
"model.layers.6.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 337 |
+
"model.layers.6.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 338 |
+
"model.layers.6.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 339 |
+
"model.layers.6.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 340 |
+
"model.layers.6.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 341 |
+
"model.layers.7.input_layernorm.weight": "model-balanced.safetensors",
|
| 342 |
+
"model.layers.7.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 343 |
+
"model.layers.7.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 344 |
+
"model.layers.7.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 345 |
+
"model.layers.7.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 346 |
+
"model.layers.7.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 347 |
+
"model.layers.7.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 348 |
+
"model.layers.7.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 349 |
+
"model.layers.7.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 350 |
+
"model.layers.8.input_layernorm.weight": "model-balanced.safetensors",
|
| 351 |
+
"model.layers.8.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 352 |
+
"model.layers.8.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 353 |
+
"model.layers.8.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 354 |
+
"model.layers.8.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 355 |
+
"model.layers.8.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 356 |
+
"model.layers.8.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 357 |
+
"model.layers.8.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 358 |
+
"model.layers.8.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 359 |
+
"model.layers.9.input_layernorm.weight": "model-balanced.safetensors",
|
| 360 |
+
"model.layers.9.mlp.down_proj.weight": "model-balanced.safetensors",
|
| 361 |
+
"model.layers.9.mlp.gate_proj.weight": "model-balanced.safetensors",
|
| 362 |
+
"model.layers.9.mlp.up_proj.weight": "model-balanced.safetensors",
|
| 363 |
+
"model.layers.9.post_attention_layernorm.weight": "model-balanced.safetensors",
|
| 364 |
+
"model.layers.9.self_attn.k_proj.weight": "model-balanced.safetensors",
|
| 365 |
+
"model.layers.9.self_attn.o_proj.weight": "model-balanced.safetensors",
|
| 366 |
+
"model.layers.9.self_attn.q_proj.weight": "model-balanced.safetensors",
|
| 367 |
+
"model.layers.9.self_attn.v_proj.weight": "model-balanced.safetensors",
|
| 368 |
+
"model.norm.weight": "model-balanced.safetensors"
|
| 369 |
+
}
|
| 370 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<|im_end|>",
|
| 11 |
+
"padding_side": "left",
|
| 12 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|
verbose/chat_template.jinja
ADDED
|
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- macro tool_to_json(tool) -%}
|
| 2 |
+
{%- set ns_tool = namespace(first=true) -%}
|
| 3 |
+
{{- '{' -}}
|
| 4 |
+
{%- for k, v in tool.items() -%}
|
| 5 |
+
{%- if k != 'defer_loading' and k != 'strict' -%}
|
| 6 |
+
{%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
|
| 7 |
+
{%- set ns_tool.first = false -%}
|
| 8 |
+
{{- '"' ~ k ~ '": ' ~ (v | tojson(ensure_ascii=False)) -}}
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- endfor -%}
|
| 11 |
+
{{- '}' -}}
|
| 12 |
+
{%- endmacro -%}
|
| 13 |
+
{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
|
| 14 |
+
{%- set low_effort = low_effort if low_effort is defined else False %}
|
| 15 |
+
{%- if reasoning_effort is defined and reasoning_effort is not none %}
|
| 16 |
+
{%- set low_effort = reasoning_effort == "low" %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
|
| 19 |
+
|
| 20 |
+
{%- set ns = namespace(last_user_idx = -1) %}
|
| 21 |
+
{%- set loop_messages = messages %}
|
| 22 |
+
{%- for m in loop_messages %}
|
| 23 |
+
{%- if m["role"] == "user" %}
|
| 24 |
+
{%- set ns.last_user_idx = loop.index0 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- endfor %}
|
| 27 |
+
|
| 28 |
+
{%- if messages[0]["role"] == "system" %}
|
| 29 |
+
{%- set system_message = messages[0]["content"] %}
|
| 30 |
+
{%- set loop_messages = messages[1:] %}
|
| 31 |
+
{%- else %}
|
| 32 |
+
{%- set system_message = "" %}
|
| 33 |
+
{%- set loop_messages = messages %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- if not tools is defined %}
|
| 36 |
+
{%- set tools = [] %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{# Recompute last_user_idx relative to loop_messages after handling system #}
|
| 39 |
+
{%- set ns = namespace(last_user_idx = -1) %}
|
| 40 |
+
{%- for m in loop_messages %}
|
| 41 |
+
{%- if m["role"] == "user" %}
|
| 42 |
+
{%- set ns.last_user_idx = loop.index0 %}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- if system_message is defined %}
|
| 46 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 47 |
+
{%- else %}
|
| 48 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 49 |
+
{{- "<|im_start|>system\n" }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 53 |
+
{%- if system_message is defined and system_message | length > 0 %}
|
| 54 |
+
{{- "\n\n" }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 57 |
+
{{- "<tools>" }}
|
| 58 |
+
{%- for tool in tools %}
|
| 59 |
+
{%- if tool.function is defined %}
|
| 60 |
+
{%- set tool = tool.function %}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- if tool.defer_loading is not defined or not tool.defer_loading %}
|
| 63 |
+
{{- '\n' ~ tool_to_json(tool) }}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{{- "\n</tools>" }}
|
| 67 |
+
|
| 68 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
{%- if system_message is defined %}
|
| 73 |
+
{{- '<|im_end|>\n' }}
|
| 74 |
+
{%- else %}
|
| 75 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
|
| 80 |
+
{%- for message in loop_messages %}
|
| 81 |
+
{%- if message.role == "assistant" %}
|
| 82 |
+
{# Add reasoning content in to content field for unified processing below. #}
|
| 83 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
|
| 84 |
+
{%- set content = "<think>\n" ~ message.reasoning_content ~ "\n</think>\n" ~ (message.content | default('', true)) %}
|
| 85 |
+
{%- else %}
|
| 86 |
+
{%- set content = message.content | default('', true) %}
|
| 87 |
+
{%- if content is string -%}
|
| 88 |
+
{# Allow downstream logic to to take care of broken thought, only handle coherent reasoning here. #}
|
| 89 |
+
{%- if '<think>' not in content and '</think>' not in content -%}
|
| 90 |
+
{%- set content = "<think></think>" ~ content -%}
|
| 91 |
+
{%- endif -%}
|
| 92 |
+
{%- else -%}
|
| 93 |
+
{%- set content = content -%}
|
| 94 |
+
{%- endif -%}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 97 |
+
{# Assistant message has tool calls. #}
|
| 98 |
+
{{- '<|im_start|>assistant\n' }}
|
| 99 |
+
{%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
|
| 100 |
+
{%- if content is string and content | trim | length > 0 %}
|
| 101 |
+
{%- if include_content %}
|
| 102 |
+
{{- (content | trim) ~ '\n' -}}
|
| 103 |
+
{%- else %}
|
| 104 |
+
{%- set c = (content | string) %}
|
| 105 |
+
{%- if '</think>' in c %}
|
| 106 |
+
{# Keep only content after the last closing think. Also generation prompt causes this. #}
|
| 107 |
+
{%- set c = c.split('</think>')[-1] %}
|
| 108 |
+
{%- elif '<think>' in c %}
|
| 109 |
+
{# If <think> was opened but never closed, drop the trailing think segment #}
|
| 110 |
+
{%- set c = c.split('<think>')[0] %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{%- set c = "<think></think>" ~ c | trim %}
|
| 113 |
+
{%- if c | length > 0 %}
|
| 114 |
+
{{- c ~ '\n' -}}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- else %}
|
| 118 |
+
{{- "<think></think>" -}}
|
| 119 |
+
{%- endif %}
|
| 120 |
+
{%- for tool_call in message.tool_calls %}
|
| 121 |
+
{%- if tool_call.function is defined %}
|
| 122 |
+
{%- set tool_call = tool_call.function %}
|
| 123 |
+
{%- endif %}
|
| 124 |
+
{{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
|
| 125 |
+
{%- if tool_call.arguments is defined %}
|
| 126 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 127 |
+
{{- '<parameter=' ~ args_name ~ '>\n' -}}
|
| 128 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 129 |
+
{{- args_value ~ '\n</parameter>\n' -}}
|
| 130 |
+
{%- endfor %}
|
| 131 |
+
{%- endif %}
|
| 132 |
+
{{- '</function>\n</tool_call>\n' -}}
|
| 133 |
+
{%- endfor %}
|
| 134 |
+
{{- '<|im_end|>\n' }}
|
| 135 |
+
{%- else %}
|
| 136 |
+
{# Assistant message doesn't have tool calls. #}
|
| 137 |
+
{%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
|
| 138 |
+
{{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
|
| 139 |
+
{%- else %}
|
| 140 |
+
{%- set c = (content | default('', true) | string) %}
|
| 141 |
+
{%- if '<think>' in c and '</think>' in c %}
|
| 142 |
+
{%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
|
| 143 |
+
{%- endif %}
|
| 144 |
+
{%- set c = c | trim %}
|
| 145 |
+
{%- if c | length > 0 %}
|
| 146 |
+
{{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
|
| 147 |
+
{%- else %}
|
| 148 |
+
{{- '<|im_start|>assistant\n<|im_end|>\n' }}
|
| 149 |
+
{%- endif %}
|
| 150 |
+
{%- endif %}
|
| 151 |
+
{%- endif %}
|
| 152 |
+
{%- elif message.role == "user" or message.role == "system" %}
|
| 153 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 154 |
+
{%- set content = message.content | string %}
|
| 155 |
+
{%- if message.role == "user" and loop.index0 == ns.last_user_idx and low_effort %}
|
| 156 |
+
{{- content + '\n\n{reasoning effort: low}' }}
|
| 157 |
+
{%- else %}
|
| 158 |
+
{{- content }}
|
| 159 |
+
{%- endif %}
|
| 160 |
+
{{- '<|im_end|>\n' }}
|
| 161 |
+
{%- elif message.role == "tool" %}
|
| 162 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 163 |
+
{{- '<|im_start|>user\n' }}
|
| 164 |
+
{%- endif %}
|
| 165 |
+
{{- '<tool_response>\n' }}
|
| 166 |
+
{{- message.content }}
|
| 167 |
+
{{- '\n</tool_response>\n' }}
|
| 168 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 169 |
+
{{- '<|im_end|>\n' }}
|
| 170 |
+
{%- elif loop.last %}
|
| 171 |
+
{{- '<|im_end|>\n' }}
|
| 172 |
+
{%- endif %}
|
| 173 |
+
{%- else %}
|
| 174 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 175 |
+
{%- endif %}
|
| 176 |
+
{%- endfor %}
|
| 177 |
+
|
| 178 |
+
{%- if add_generation_prompt %}
|
| 179 |
+
{%- if enable_thinking %}
|
| 180 |
+
{{- '<|im_start|>assistant\n<think>\n' }}
|
| 181 |
+
{%- else %}
|
| 182 |
+
{{- '<|im_start|>assistant\n<think></think>' }}
|
| 183 |
+
{%- endif %}
|
| 184 |
+
{%- endif %}
|
verbose/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 100283,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"embedding_multiplier": 1.0,
|
| 11 |
+
"eos_token_id": 100257,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 4096,
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 12800,
|
| 16 |
+
"logits_scaling": 1.0,
|
| 17 |
+
"max_position_embeddings": 131072,
|
| 18 |
+
"mlp_bias": false,
|
| 19 |
+
"model_type": "granite",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 40,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"pad_token_id": 100257,
|
| 24 |
+
"residual_multiplier": 1.0,
|
| 25 |
+
"rms_norm_eps": 1e-05,
|
| 26 |
+
"rope_parameters": {
|
| 27 |
+
"rope_theta": 10000000,
|
| 28 |
+
"rope_type": "default"
|
| 29 |
+
},
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"transformers_version": "5.5.3",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 100352
|
| 34 |
+
}
|
verbose/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100283,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 100257,
|
| 6 |
+
"pad_token_id": 100257,
|
| 7 |
+
"temperature": 1.0,
|
| 8 |
+
"top_p": 0.95,
|
| 9 |
+
"transformers_version": "5.5.3"
|
| 10 |
+
}
|
verbose/model-verbose.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f582543fcb077e8672e6c05aba680e3d90b35601390817cea1af20ff2733fbd1
|
| 3 |
+
size 17583228544
|
verbose/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 17583185920
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-verbose.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-verbose.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-verbose.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-verbose.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-verbose.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-verbose.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-verbose.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-verbose.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-verbose.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-verbose.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-verbose.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-verbose.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-verbose.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-verbose.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-verbose.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-verbose.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-verbose.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-verbose.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-verbose.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-verbose.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-verbose.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-verbose.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-verbose.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-verbose.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-verbose.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-verbose.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-verbose.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-verbose.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 242 |
+
"model.layers.32.input_layernorm.weight": "model-verbose.safetensors",
|
| 243 |
+
"model.layers.32.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 245 |
+
"model.layers.32.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 251 |
+
"model.layers.33.input_layernorm.weight": "model-verbose.safetensors",
|
| 252 |
+
"model.layers.33.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 254 |
+
"model.layers.33.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 260 |
+
"model.layers.34.input_layernorm.weight": "model-verbose.safetensors",
|
| 261 |
+
"model.layers.34.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 263 |
+
"model.layers.34.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 269 |
+
"model.layers.35.input_layernorm.weight": "model-verbose.safetensors",
|
| 270 |
+
"model.layers.35.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 272 |
+
"model.layers.35.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 278 |
+
"model.layers.36.input_layernorm.weight": "model-verbose.safetensors",
|
| 279 |
+
"model.layers.36.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 281 |
+
"model.layers.36.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 287 |
+
"model.layers.37.input_layernorm.weight": "model-verbose.safetensors",
|
| 288 |
+
"model.layers.37.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 290 |
+
"model.layers.37.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 296 |
+
"model.layers.38.input_layernorm.weight": "model-verbose.safetensors",
|
| 297 |
+
"model.layers.38.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 299 |
+
"model.layers.38.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 305 |
+
"model.layers.39.input_layernorm.weight": "model-verbose.safetensors",
|
| 306 |
+
"model.layers.39.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 308 |
+
"model.layers.39.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 314 |
+
"model.layers.4.input_layernorm.weight": "model-verbose.safetensors",
|
| 315 |
+
"model.layers.4.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 317 |
+
"model.layers.4.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 323 |
+
"model.layers.5.input_layernorm.weight": "model-verbose.safetensors",
|
| 324 |
+
"model.layers.5.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 325 |
+
"model.layers.5.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 326 |
+
"model.layers.5.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 327 |
+
"model.layers.5.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 328 |
+
"model.layers.5.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 329 |
+
"model.layers.5.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 330 |
+
"model.layers.5.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 331 |
+
"model.layers.5.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 332 |
+
"model.layers.6.input_layernorm.weight": "model-verbose.safetensors",
|
| 333 |
+
"model.layers.6.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 334 |
+
"model.layers.6.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 335 |
+
"model.layers.6.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 336 |
+
"model.layers.6.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 337 |
+
"model.layers.6.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 338 |
+
"model.layers.6.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 339 |
+
"model.layers.6.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 340 |
+
"model.layers.6.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 341 |
+
"model.layers.7.input_layernorm.weight": "model-verbose.safetensors",
|
| 342 |
+
"model.layers.7.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 343 |
+
"model.layers.7.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 344 |
+
"model.layers.7.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 345 |
+
"model.layers.7.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 346 |
+
"model.layers.7.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 347 |
+
"model.layers.7.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 348 |
+
"model.layers.7.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 349 |
+
"model.layers.7.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 350 |
+
"model.layers.8.input_layernorm.weight": "model-verbose.safetensors",
|
| 351 |
+
"model.layers.8.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 352 |
+
"model.layers.8.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 353 |
+
"model.layers.8.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 354 |
+
"model.layers.8.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 355 |
+
"model.layers.8.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 356 |
+
"model.layers.8.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 357 |
+
"model.layers.8.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 358 |
+
"model.layers.8.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 359 |
+
"model.layers.9.input_layernorm.weight": "model-verbose.safetensors",
|
| 360 |
+
"model.layers.9.mlp.down_proj.weight": "model-verbose.safetensors",
|
| 361 |
+
"model.layers.9.mlp.gate_proj.weight": "model-verbose.safetensors",
|
| 362 |
+
"model.layers.9.mlp.up_proj.weight": "model-verbose.safetensors",
|
| 363 |
+
"model.layers.9.post_attention_layernorm.weight": "model-verbose.safetensors",
|
| 364 |
+
"model.layers.9.self_attn.k_proj.weight": "model-verbose.safetensors",
|
| 365 |
+
"model.layers.9.self_attn.o_proj.weight": "model-verbose.safetensors",
|
| 366 |
+
"model.layers.9.self_attn.q_proj.weight": "model-verbose.safetensors",
|
| 367 |
+
"model.layers.9.self_attn.v_proj.weight": "model-verbose.safetensors",
|
| 368 |
+
"model.norm.weight": "model-verbose.safetensors"
|
| 369 |
+
}
|
| 370 |
+
}
|
verbose/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
verbose/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<|im_end|>",
|
| 11 |
+
"padding_side": "left",
|
| 12 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|