Instructions to use m-a-p/OpenCodeInterpreter-SC2-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use m-a-p/OpenCodeInterpreter-SC2-3B with Transformers:

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

pipe = pipeline("text-generation", model="m-a-p/OpenCodeInterpreter-SC2-3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("m-a-p/OpenCodeInterpreter-SC2-3B")
model = AutoModelForCausalLM.from_pretrained("m-a-p/OpenCodeInterpreter-SC2-3B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use m-a-p/OpenCodeInterpreter-SC2-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "m-a-p/OpenCodeInterpreter-SC2-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "m-a-p/OpenCodeInterpreter-SC2-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/m-a-p/OpenCodeInterpreter-SC2-3B

SGLang

How to use m-a-p/OpenCodeInterpreter-SC2-3B 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 "m-a-p/OpenCodeInterpreter-SC2-3B" \
    --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": "m-a-p/OpenCodeInterpreter-SC2-3B",
		"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 "m-a-p/OpenCodeInterpreter-SC2-3B" \
        --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": "m-a-p/OpenCodeInterpreter-SC2-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use m-a-p/OpenCodeInterpreter-SC2-3B with Docker Model Runner:
```
docker model run hf.co/m-a-p/OpenCodeInterpreter-SC2-3B
```

aaabiao

muhtasham commited on Mar 2, 2024

Commit

8a9a396

verified ·

1 Parent(s): f399777

Update config.json (#2)

Browse files

- Update config.json (d523e2238d7bfcf459262cebbe24856dfd22d49a)

Co-authored-by: Muhtasham Oblokulov <muhtasham@users.noreply.huggingface.co>

Files changed (1) hide show

config.json +1 -0

config.json CHANGED Viewed

@@ -22,6 +22,7 @@
   "residual_dropout": 0.0,
   "rope_theta": 999999.4420358813,
   "sliding_window": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
   "use_bias": true,

   "residual_dropout": 0.0,
   "rope_theta": 999999.4420358813,
   "sliding_window": 4096,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
   "use_bias": true,