Instructions to use m-a-p/OpenCodeInterpreter-CL-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use m-a-p/OpenCodeInterpreter-CL-34B with Transformers:

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

pipe = pipeline("text-generation", model="m-a-p/OpenCodeInterpreter-CL-34B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("m-a-p/OpenCodeInterpreter-CL-34B")
model = AutoModelForCausalLM.from_pretrained("m-a-p/OpenCodeInterpreter-CL-34B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use m-a-p/OpenCodeInterpreter-CL-34B 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-34B"
# 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-34B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/m-a-p/OpenCodeInterpreter-CL-34B

SGLang

How to use m-a-p/OpenCodeInterpreter-CL-34B 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-34B" \
    --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-34B",
		"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-34B" \
        --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-34B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use m-a-p/OpenCodeInterpreter-CL-34B with Docker Model Runner:
```
docker model run hf.co/m-a-p/OpenCodeInterpreter-CL-34B
```

aaabiao commited on Mar 1, 2024

Commit

9f5d45c

verified ·

1 Parent(s): f620f98

Update README.md

Browse files

Files changed (1) hide show

README.md +33 -0

README.md CHANGED Viewed

@@ -27,6 +27,39 @@ For further information and related work, refer to our paper: ["OpenCodeInterpre
 ## Model Information
 This model is based on [CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf).
 ## Model Usage
 ### Inference

 ## Model Information
 This model is based on [CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf).
+## Benchmark Scores
+The OpenCodeInterpreter Models series exemplifies the evolution of coding model performance, particularly highlighting the significant enhancements brought about by the integration of execution feedback. In an effort to quantify these improvements, we present a detailed comparison across two critical benchmarks: HumanEval and MBPP. This comparison not only showcases the individual performance metrics on each benchmark but also provides an aggregated view of the overall performance enhancement. The subsequent table succinctly encapsulates the performance data, offering a clear perspective on how execution feedback contributes to elevating the models' capabilities in code interpretation and execution tasks.
+| **Benchmark** | **HumanEval (+)** | **MBPP (+)** | **Average (+)** |
+|---------------|-------------------|--------------|-----------------|
+| **OpenCodeInterpreter-DS-1.3B** | 65.2 (61.0) | 63.4 (52.4) | 64.3 (56.7) |
+| + Execution Feedback | 65.2 (62.2) | 65.2 (55.6) | 65.2 (58.9) |
+| **OpenCodeInterpreter-DS-6.7B** | 76.2 (72.0) | 73.9 (63.7) | 75.1 (67.9) |
+| + Execution Feedback | 81.1 (78.7) | 82.7 (72.4) | 81.9 (75.6) |
+| + Synth. Human Feedback | 87.2 (86.6) | 86.2 (74.2) | 86.7 (80.4) |
+| + Synth. Human Feedback (Oracle) | 89.7 (86.6) | 87.2 (75.2) | 88.5 (80.9) |
+| **OpenCodeInterpreter-DS-33B** | 79.3 (74.3) | 78.7 (66.4) | 79.0 (70.4) |
+| + Execution Feedback | 82.9 (80.5) | 83.5 (72.2) | 83.2 (76.4) |
+| + Synth. Human Feedback | 88.4 (86.0) | 87.5 (75.9) | 88.0 (81.0) |
+| + Synth. Human Feedback (Oracle) | 92.7 (89.7) | 90.5 (79.5) | 91.6 (84.6) |
+| **OpenCodeInterpreter-CL-7B** | 72.6 (67.7) | 66.4 (55.4) | 69.5 (61.6) |
+| + Execution Feedback | 75.6 (70.1) | 69.9 (60.7) | 72.8 (65.4) |
+| **OpenCodeInterpreter-CL-13B** | 77.4 (73.8) | 70.7 (59.2) | 74.1 (66.5) |
+| + Execution Feedback | 81.1 (76.8) | 78.2 (67.2) | 79.7 (72.0) |
+| **OpenCodeInterpreter-CL-34B** | 78.0 (72.6) | 73.4 (61.4) | 75.7 (67.0) |
+| + Execution Feedback | 81.7 (78.7) | 80.2 (67.9) | 81.0 (73.3) |
+| **OpenCodeInterpreter-CL-70B** | 76.2 (70.7) | 73.0 (61.9) | 74.6 (66.3) |
+| + Execution Feedback | 79.9 (77.4) | 81.5 (69.9) | 80.7 (73.7) |
+| **OpenCodeInterpreter-GM-7B** | 56.1 (50.0) | 39.8 (34.6) | 48.0 (42.3) |
+| + Execution Feedback | 64.0 (54.3) | 48.6 (40.9) | 56.3 (47.6) |
+| **OpenCodeInterpreter-STAR-3B** | 65.2 (57.9) | 62.7 (52.9) | 64.0 (55.4) |
+| + Execution Feedback | 67.1 (60.4) | 63.4 (54.9) | 65.3 (57.7) |
+| **OpenCodeInterpreter-STAR-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.*
 ## Model Usage
 ### Inference