Upload README.md

README.md

@@ -1,6 +1,7 @@
 ---
 license: mit
 library_name: transformers
+base_model: deepseek-ai/DeepSeek-V3.1
 ---
 # DeepSeek-V3.1
 
@@ -46,7 +47,7 @@ library_name: transformers
 
 DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:
 
-- **Hybrid thinking mode**: One model supports both thinking mode and non-thinking mode by changing the chat template. 
+- **Hybrid thinking mode**: One model supports both thinking mode and non-thinking mode by changing the chat template.
 
 - **Smarter tool calling**: Through post-training optimization, the model's performance in tool usage and agent tasks has significantly improved.
 
@@ -93,7 +94,7 @@ By concatenating the context and the prefix, we obtain the correct prompt for th
 Prefix:
 `<｜begin▁of▁sentence｜>{system prompt}<｜User｜>{query}<｜Assistant｜><think>`
 
-The prefix of thinking mode is similar to DeepSeek-R1. 
+The prefix of thinking mode is similar to DeepSeek-R1.
 
 
 #### Multi-Turn
@@ -103,12 +104,12 @@ Context:
 Prefix:
 `<｜User｜>{query}<｜Assistant｜><think>`
 
-The multi-turn template is the same with non-thinking multi-turn chat template. It means the thinking token in the last turn will be dropped but the `</think>` is retained in every turn of context. 
+The multi-turn template is the same with non-thinking multi-turn chat template. It means the thinking token in the last turn will be dropped but the `</think>` is retained in every turn of context.
 
 ### ToolCall
-Toolcall is supported in non-thinking mode. The format is: 
+Toolcall is supported in non-thinking mode. The format is:
 
-`<｜begin▁of▁sentence｜>{system prompt}{tool_description}<｜User｜>{query}<｜Assistant｜></think>` where the tool_description is 
+`<｜begin▁of▁sentence｜>{system prompt}{tool_description}<｜User｜>{query}<｜Assistant｜></think>` where the tool_description is
 
 ```
 ## Tools
@@ -132,7 +133,7 @@ Where:
 We support various code agent frameworks. Please refer to the above toolcall format to create your own code agents. An example is shown in `assets/code_agent_trajectory.html`.
 
 ### Search-Agent
-We design a specific format for searching toolcall in thinking mode, to support search agent. 
+We design a specific format for searching toolcall in thinking mode, to support search agent.
 
 For complex questions that require accessing external or up-to-date information, DeepSeek-V3.1 can leverage a user-provided search tool through a multi-turn tool-calling process.
 
@@ -146,7 +147,7 @@ Please refer to the `assets/search_tool_trajectory.html` and `assets/search_pyth
 |          | MMLU-Pro (EM)                  | 83.7  | 81.2    | 84.8          | 85.0
 |          | GPQA-Diamond (Pass@1)           | 74.9   | 68.4   | 80.1            | 81.0
 |          | Humanity's Last Exam (Pass@1)   | -    |       -            | 15.9         | 17.7
-|Search Agent| 
+|Search Agent|
 |          | BrowseComp       | -      | -  | 30.0 | 8.9
 |          | BrowseComp_zh       | -     | -  | 49.2      | 35.7
 |          | Humanity's Last Exam (Python + Search)      |-   | -    | 29.8         | 24.8
@@ -164,8 +165,8 @@ Please refer to the `assets/search_tool_trajectory.html` and `assets/search_pyth
 |          | AIME 2025 (Pass@1)                     | 49.8  | 51.3 | 88.4          | 87.5
 |          | HMMT 2025 (Pass@1)        | 33.5    | 29.2   | 84.2 | 79.4 |
 
-Note: 
-- Search agents are evaluated with our internal search framework, which uses a commercial search API + webpage filter + 128K context window. Seach agent results of R1-0528 are evaluated with a pre-defined workflow. 
+Note:
+- Search agents are evaluated with our internal search framework, which uses a commercial search API + webpage filter + 128K context window. Seach agent results of R1-0528 are evaluated with a pre-defined workflow.
 
 - SWE-bench is evaluated with our internal code agent framework.
 
@@ -204,13 +205,13 @@ This repository and the model weights are licensed under the [MIT License](LICEN
 
 ```
 @misc{deepseekai2024deepseekv3technicalreport,
-      title={DeepSeek-V3 Technical Report}, 
+      title={DeepSeek-V3 Technical Report},
       author={DeepSeek-AI},
       year={2024},
       eprint={2412.19437},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2412.19437}, 
+      url={https://arxiv.org/abs/2412.19437},
 }
 ```