Instructions to use bigcode/octocoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigcode/octocoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigcode/octocoder")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bigcode/octocoder", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigcode/octocoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigcode/octocoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigcode/octocoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigcode/octocoder
- SGLang
How to use bigcode/octocoder 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 "bigcode/octocoder" \ --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": "bigcode/octocoder", "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 "bigcode/octocoder" \ --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": "bigcode/octocoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigcode/octocoder with Docker Model Runner:
docker model run hf.co/bigcode/octocoder
Commit ·
08466d2
1
Parent(s): 09a617d
Update README.md
Browse files
README.md
CHANGED
|
@@ -84,7 +84,7 @@ OctoCoder is an instruction tuned model with 15.5B parameters created by finetun
|
|
| 84 |
<td>CodeGeeX2 (6B parameters) instruction tuned on CommitPackFT + OASST</td>
|
| 85 |
</tr>
|
| 86 |
<tr>
|
| 87 |
-
<th>Evaluation
|
| 88 |
<th><a href=https://huggingface.co/datasets/bigcode/humanevalpack>HumanEvalPack</a></th>
|
| 89 |
<td>Extension of OpenAI's HumanEval to cover 3 scenarios across 6 languages</td>
|
| 90 |
</tr>
|
|
|
|
| 84 |
<td>CodeGeeX2 (6B parameters) instruction tuned on CommitPackFT + OASST</td>
|
| 85 |
</tr>
|
| 86 |
<tr>
|
| 87 |
+
<th>Evaluation </t>
|
| 88 |
<th><a href=https://huggingface.co/datasets/bigcode/humanevalpack>HumanEvalPack</a></th>
|
| 89 |
<td>Extension of OpenAI's HumanEval to cover 3 scenarios across 6 languages</td>
|
| 90 |
</tr>
|