Instructions to use facebook/incoder-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/incoder-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="facebook/incoder-1B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("facebook/incoder-1B") model = AutoModelForCausalLM.from_pretrained("facebook/incoder-1B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use facebook/incoder-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "facebook/incoder-1B" # 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-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/facebook/incoder-1B
- SGLang
How to use facebook/incoder-1B 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-1B" \ --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-1B", "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-1B" \ --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-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use facebook/incoder-1B with Docker Model Runner:
docker model run hf.co/facebook/incoder-1B
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# InCoder 1B
|
| 2 |
|
| 3 |
A 1B parameter decoder-only Transformer model trained on code using a causal-masked objective, which allows inserting/infilling code as well as standard left-to-right generation.
|
|
@@ -27,6 +35,10 @@ pip install git+https://github.com/huggingface/transformers
|
|
| 27 |
|
| 28 |
See [https://github.com/dpfried/incoder](https://github.com/dpfried/incoder) for example code.
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
## Credits
|
| 31 |
|
| 32 |
The model was developed by Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer and Mike Lewis.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: "cc-by-nc-4.0"
|
| 3 |
+
tags:
|
| 4 |
+
- code
|
| 5 |
+
- python
|
| 6 |
+
- javascript
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
# InCoder 1B
|
| 10 |
|
| 11 |
A 1B parameter decoder-only Transformer model trained on code using a causal-masked objective, which allows inserting/infilling code as well as standard left-to-right generation.
|
|
|
|
| 35 |
|
| 36 |
See [https://github.com/dpfried/incoder](https://github.com/dpfried/incoder) for example code.
|
| 37 |
|
| 38 |
+
## License
|
| 39 |
+
|
| 40 |
+
CC-BY-NC 4.0
|
| 41 |
+
|
| 42 |
## Credits
|
| 43 |
|
| 44 |
The model was developed by Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer and Mike Lewis.
|