Text Generation
Transformers
PyTorch
gpt_bigcode
fill-mask
code
Eval Results (legacy)
text-generation-inference
Instructions to use bigcode/santacoderpack with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigcode/santacoderpack with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigcode/santacoderpack")# Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("bigcode/santacoderpack") model = AutoModelWithLMHead.from_pretrained("bigcode/santacoderpack") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigcode/santacoderpack with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigcode/santacoderpack" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigcode/santacoderpack", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigcode/santacoderpack
- SGLang
How to use bigcode/santacoderpack 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/santacoderpack" \ --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/santacoderpack", "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/santacoderpack" \ --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/santacoderpack", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigcode/santacoderpack with Docker Model Runner:
docker model run hf.co/bigcode/santacoderpack
Commit ·
ea5895e
1
Parent(s): 63c09f2
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ widget:
|
|
| 7 |
group: Python
|
| 8 |
license: bigcode-openrail-m
|
| 9 |
datasets:
|
| 10 |
-
- bigcode/
|
| 11 |
metrics:
|
| 12 |
- code_eval
|
| 13 |
library_name: transformers
|
|
@@ -101,7 +101,7 @@ model-index:
|
|
| 101 |
SantaCoderPack is an pre-trained model with the same architecture of SantaCoder on
|
| 102 |
<th><a href=https://huggingface.co/datasets/bigcode/commitpack>CommitPack</a> using this format:
|
| 103 |
|
| 104 |
-
```
|
| 105 |
<commit_before>code_before<commit_msg>message<commit_after>code_after
|
| 106 |
```
|
| 107 |
|
|
|
|
| 7 |
group: Python
|
| 8 |
license: bigcode-openrail-m
|
| 9 |
datasets:
|
| 10 |
+
- bigcode/commitpack-subset-cf
|
| 11 |
metrics:
|
| 12 |
- code_eval
|
| 13 |
library_name: transformers
|
|
|
|
| 101 |
SantaCoderPack is an pre-trained model with the same architecture of SantaCoder on
|
| 102 |
<th><a href=https://huggingface.co/datasets/bigcode/commitpack>CommitPack</a> using this format:
|
| 103 |
|
| 104 |
+
```
|
| 105 |
<commit_before>code_before<commit_msg>message<commit_after>code_after
|
| 106 |
```
|
| 107 |
|