Instructions to use remiai3/Math_model_qwen2.5_1.5b_project_guide with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use remiai3/Math_model_qwen2.5_1.5b_project_guide with Transformers:

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

pipe = pipeline("text-generation", model="remiai3/Math_model_qwen2.5_1.5b_project_guide")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("remiai3/Math_model_qwen2.5_1.5b_project_guide", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use remiai3/Math_model_qwen2.5_1.5b_project_guide with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "remiai3/Math_model_qwen2.5_1.5b_project_guide"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "remiai3/Math_model_qwen2.5_1.5b_project_guide",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/remiai3/Math_model_qwen2.5_1.5b_project_guide

SGLang

How to use remiai3/Math_model_qwen2.5_1.5b_project_guide 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 "remiai3/Math_model_qwen2.5_1.5b_project_guide" \
    --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": "remiai3/Math_model_qwen2.5_1.5b_project_guide",
		"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 "remiai3/Math_model_qwen2.5_1.5b_project_guide" \
        --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": "remiai3/Math_model_qwen2.5_1.5b_project_guide",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use remiai3/Math_model_qwen2.5_1.5b_project_guide with Docker Model Runner:
```
docker model run hf.co/remiai3/Math_model_qwen2.5_1.5b_project_guide
```

A newer version of this model is available: Qwen/Qwen2.5-1.5B-Instruct

library_name: transformerslicense: apache-2.0 base_model: Qwen/Qwen2.5-1.5B-Instruct: - instruction-tuned - mathematical-reasoning - text-generation - cpu-compatible Qwen/Qwen2.5-1.5B-Instruct Local Setup Guide Overview This repository, hosted by remiai3, provides free resources for students to run the Qwen/Qwen2.5-1.5B-Instruct model locally for research and experimental purposes. It includes scripts, documentation, and setup instructions, with no fees or hidden charges. Model Details

Name:Qwen/Qwen2.5-1.5B-Instruct Organization: Qwen (Alibaba Cloud) Attributes: 2.5 billion parameters Instruction-tuned for mathematical reasoning and text generation Supports float16 precision for CPU efficiency License: Apache-2.0

Original Repository: Qwen/Qwen2.5-1.5B-Instruct

Setup

Clone this repository: git clone https://huggingface.co/remiai3 Install dependencies: pip install -r requirements.txt Download model weights from the original repository using your Hugging Face token. Run the provided scripts to download and test the model.

Requirements

Python 3.10.9 (must needed) Minimum 16GB RAM (24GB recommended for finetuning) ~5GB disk space for model weights Internet connection for downloading weights

Usage

Use download_model.py to download the model weights. Run test_model.py for inference (e.g., solving math problems). Optionally, use app.py for a web-based interface. Refer to documents.txt for detailed instructions.

License This repository is free for student use. The model weights are licensed under Apache-2.0 by Qwen. See the original repository for details. Contact Open a discussion on the remiai3 repository for support or questions.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for remiai3/Math_model_qwen2.5_1.5b_project_guide

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Finetuned

(1556)

this model