Sri-Vigneshwar-DJ/phi-4-GGUF

This model was converted to GGUF format from Sri-Vigneshwar-DJ/phi-4-GGUF using llama.cpp Refer to the original model card for more details on the model.

Model Summary

Developers	Microsoft Research
Description	phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning. phi-4 underwent a rigorous enhancement and alignment process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures
Architecture	14B parameters, dense decoder-only Transformer model
Inputs	Text, best suited for prompts in the chat format
Context length	16K tokens
GPUs	1920 H100-80G
Training time	21 days
Training data	9.8T tokens
Outputs	Generated text in response to input
Dates	October 2024 – November 2024
Status	Static model trained on an offline dataset with cutoff dates of June 2024 and earlier for publicly available data
Release date	December 12, 2024
License	MIT

Intended Use

Primary Use Cases	Our model is designed to accelerate research on language models, for use as a building block for generative AI powered features. It provides uses for general purpose AI systems and applications (primarily in English) which require: 1. Memory/compute constrained environments. 2. Latency bound scenarios. 3. Reasoning and logic.
Out-of-Scope Use Cases	Our models is not specifically designed or evaluated for all downstream purposes, thus: 1. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fairness before using within a specific downstream use case, particularly for high-risk scenarios. 2. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case, including the model’s focus on English. 3. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux) from []

brew install llama.cpp or !git clone https://github.com/ggerganov/llama.cpp.git

Invoke the llama.cpp server or the CLI.

CLI:

! /content/llama.cpp/llama-cli -m ./models/phi-4 -n 90 --repeat_penalty 1.0 --color -i -r "User:" -f /content/llama.cpp/prompts/chat-with-bob.txt

or

llama-cli --hf-repo Sri-Vigneshwar-DJ/phi-4-GGUF --hf-file FP8.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Sri-Vigneshwar-DJ/sarvam-2b-v0.5-GGUF --hf-file FP8.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag or ''!make GGML_OPENBLAS=1' along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

or

!make GGML_OPENBLAS=1

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Sri-Vigneshwar-DJ/phi-4-GGUF --hf-file FP8.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Sri-Vigneshwar-DJ/phi-4-GGUF --hf-file sFP8.gguf -c 2048