Instructions to use facebook/incoder-6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/incoder-6B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="facebook/incoder-6B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("facebook/incoder-6B") model = AutoModelForCausalLM.from_pretrained("facebook/incoder-6B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use facebook/incoder-6B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "facebook/incoder-6B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "facebook/incoder-6B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/facebook/incoder-6B
- SGLang
How to use facebook/incoder-6B 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 "facebook/incoder-6B" \ --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": "facebook/incoder-6B", "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 "facebook/incoder-6B" \ --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": "facebook/incoder-6B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use facebook/incoder-6B with Docker Model Runner:
docker model run hf.co/facebook/incoder-6B
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,10 +6,10 @@ The model was trained on public open-source repositories with a permissive, non-
|
|
| 6 |
|
| 7 |
For more information, see our:
|
| 8 |
|
|
|
|
| 9 |
- [Project site](https://sites.google.com/view/incoder-code-models)
|
| 10 |
-
- [Paper](https://github.com/dpfried/incoder/blob/main/paper/InCoder.pdf)
|
| 11 |
- [Examples](https://sites.google.com/view/incoder-code-models/home/examples)
|
| 12 |
-
- [
|
| 13 |
|
| 14 |
A smaller, 1B, parameter model is also available at [facebook/incoder-1B](https://huggingface.co/facebook/incoder-1B).
|
| 15 |
|
|
|
|
| 6 |
|
| 7 |
For more information, see our:
|
| 8 |
|
| 9 |
+
- [Demo](https://huggingface.co/spaces/facebook/incoder-demo)
|
| 10 |
- [Project site](https://sites.google.com/view/incoder-code-models)
|
|
|
|
| 11 |
- [Examples](https://sites.google.com/view/incoder-code-models/home/examples)
|
| 12 |
+
- [Paper](https://github.com/dpfried/incoder/blob/main/paper/InCoder.pdf)
|
| 13 |
|
| 14 |
A smaller, 1B, parameter model is also available at [facebook/incoder-1B](https://huggingface.co/facebook/incoder-1B).
|
| 15 |
|