Instructions to use DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode")
model = AutoModelForCausalLM.from_pretrained("DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode

SGLang

How to use DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode with Docker Model Runner:
```
docker model run hf.co/DeryFerd/Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode
```

DeryFerd commited on Sep 29, 2025

Commit

8b67688

verified ·

1 Parent(s): bdfa374

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ pipeline_tag: text-generation
 **UPDATE:** This model is a fine-tuned, versatile version of **`microsoft/phi-2`**, adapted for both **Python code generation** and **step-by-step mathematical reasoning**. The goal of this project was to distill the capabilities of larger "teacher" models (`Qwen2.5-Coder-7B-Instruct` for coding and `Qwen2.5-Math-7B-Instruct` for math) into the compact and efficient Phi-2 architecture.
-The model was trained on a combined dataset of Python programming problems (from MBPP) and grade-school math word problems (from GSM8K and MATH). It is designed to generate not just answers, but also the thought process behind them, mimicking the style of its teachers.
 - **Developed by:** DeryFerd
 - **Model type:** Causal Language Model
@@ -56,7 +56,7 @@ This is a specialized model. It will not perform well on tasks outside of basic
 ## Bias, Risks, and Limitations
-This model was trained on the MBPP, GSM8K, and MATH datasets. Its capabilities are limited to these domains. The model may generate code that is syntactically correct but logically flawed, or math solutions that seem logical but contain calculation errors. **Always review and test the generated output before use in production environments.**
 A notable limitation discovered during development is a potential **low-level GPU memory conflict**. When this model is loaded into the same runtime as a significantly larger and architecturally different model (like Qwen 7B), its fine-tuned capabilities can be silently overridden, causing it to revert to the base model's behavior. It is recommended to run this model in an isolated process.

 **UPDATE:** This model is a fine-tuned, versatile version of **`microsoft/phi-2`**, adapted for both **Python code generation** and **step-by-step mathematical reasoning**. The goal of this project was to distill the capabilities of larger "teacher" models (`Qwen2.5-Coder-7B-Instruct` for coding and `Qwen2.5-Math-7B-Instruct` for math) into the compact and efficient Phi-2 architecture.
+The model was trained on a combined dataset of Python programming problems (from MBPP and opc-sft-stage2) and grade-school math word problems (from GSM8K and MATH). It is designed to generate not just answers, but also the thought process behind them, mimicking the style of its teachers.
 - **Developed by:** DeryFerd
 - **Model type:** Causal Language Model
 ## Bias, Risks, and Limitations
+This model was trained on the MBPP, opc-sft-stage2, GSM8K, and MATH datasets. Its capabilities are limited to these domains. The model may generate code that is syntactically correct but logically flawed, or math solutions that seem logical but contain calculation errors. **Always review and test the generated output before use in production environments.**
 A notable limitation discovered during development is a potential **low-level GPU memory conflict**. When this model is loaded into the same runtime as a significantly larger and architecturally different model (like Qwen 7B), its fine-tuned capabilities can be silently overridden, causing it to revert to the base model's behavior. It is recommended to run this model in an isolated process.