Instructions to use ise-uiuc/Magicoder-CL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ise-uiuc/Magicoder-CL-7B with Transformers:

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

pipe = pipeline("text-generation", model="ise-uiuc/Magicoder-CL-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ise-uiuc/Magicoder-CL-7B")
model = AutoModelForCausalLM.from_pretrained("ise-uiuc/Magicoder-CL-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ise-uiuc/Magicoder-CL-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ise-uiuc/Magicoder-CL-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ise-uiuc/Magicoder-CL-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ise-uiuc/Magicoder-CL-7B

SGLang

How to use ise-uiuc/Magicoder-CL-7B 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 "ise-uiuc/Magicoder-CL-7B" \
    --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": "ise-uiuc/Magicoder-CL-7B",
		"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 "ise-uiuc/Magicoder-CL-7B" \
        --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": "ise-uiuc/Magicoder-CL-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ise-uiuc/Magicoder-CL-7B with Docker Model Runner:
```
docker model run hf.co/ise-uiuc/Magicoder-CL-7B
```

Delete model-00005-of-00006.safetensors

by Judith76 - opened about 15 hours ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Judith76

about 15 hours ago

Hi, thanks for posting this detailed overview of Magicoder-CL-7B. The combination of the OSS-Instruct-75K dataset, the Llama architecture, and the text-generation-inference setup looks really solid for intelligent software engineering tasks. I also appreciate you sharing the arXiv references (2312.02120 and 2305.06161) and the license info—it definitely helps when evaluating models for real-world use. The safetensors file structure seems well organized too.

On a slightly different note, if you ever need a break from all this heavy coding and model fine-tuning, I recently stumbled upon a site that offers a surprisingly fun gaming experience. It’s not AI-related at all, but it's a great way to relax and recharge between training runs. You can check it out right here if you're interested. I was genuinely impressed by what it offers, and I thought I'd share it as a casual recommendation. Thanks!

Delete model-00005-of-00006.safetensors5d15b276

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment