Instructions to use m-a-p/OpenCodeInterpreter-CL-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use m-a-p/OpenCodeInterpreter-CL-13B with Transformers:

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

pipe = pipeline("text-generation", model="m-a-p/OpenCodeInterpreter-CL-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("m-a-p/OpenCodeInterpreter-CL-13B")
model = AutoModelForCausalLM.from_pretrained("m-a-p/OpenCodeInterpreter-CL-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use m-a-p/OpenCodeInterpreter-CL-13B 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-CL-13B"
# 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-CL-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/m-a-p/OpenCodeInterpreter-CL-13B

SGLang

How to use m-a-p/OpenCodeInterpreter-CL-13B 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-CL-13B" \
    --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-CL-13B",
		"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-CL-13B" \
        --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-CL-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use m-a-p/OpenCodeInterpreter-CL-13B with Docker Model Runner:
```
docker model run hf.co/m-a-p/OpenCodeInterpreter-CL-13B
```

aaabiao commited on Mar 3, 2024

Commit

e46c2aa

verified ·

1 Parent(s): a19fc7d

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -57,6 +57,8 @@ The OpenCodeInterpreter Models series exemplifies the evolution of coding model
 | + Execution Feedback | 67.1 (60.4) | 63.4 (54.9) | 65.3 (57.7) |
 | **OpenCodeInterpreter-SC2-7B** | 73.8 (68.9) | 61.7 (51.1) | 67.8 (60.0) |
 | + Execution Feedback | 75.6 (69.5) | 66.9 (55.4) | 71.3 (62.5) |
 *Note: The "(+)" notation represents scores from extended versions of the HumanEval and MBPP benchmarks. To ensure a fair comparison, the results shown for adding execution feedback are based on outcomes after just one iteration of feedback, without unrestricted iterations. This approach highlights the immediate impact of execution feedback on performance improvements across benchmarks.*

 | + Execution Feedback | 67.1 (60.4) | 63.4 (54.9) | 65.3 (57.7) |
 | **OpenCodeInterpreter-SC2-7B** | 73.8 (68.9) | 61.7 (51.1) | 67.8 (60.0) |
 | + Execution Feedback | 75.6 (69.5) | 66.9 (55.4) | 71.3 (62.5) |
+| **OpenCodeInterpreter-SC2-15B** | 75.6 (69.5) | 71.2 (61.2) | 73.4 (65.4) |
+| + Execution Feedback | 77.4 (72.0) | 74.2 (63.4) | 75.8 (67.7) |
 *Note: The "(+)" notation represents scores from extended versions of the HumanEval and MBPP benchmarks. To ensure a fair comparison, the results shown for adding execution feedback are based on outcomes after just one iteration of feedback, without unrestricted iterations. This approach highlights the immediate impact of execution feedback on performance improvements across benchmarks.*