Text Generation
Transformers
Safetensors
English
starcoder2
code
starcoder
bigcode
sft
7b
text-generation-inference
Instructions to use abideen/starcoder2-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abideen/starcoder2-chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="abideen/starcoder2-chat")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("abideen/starcoder2-chat") model = AutoModelForCausalLM.from_pretrained("abideen/starcoder2-chat") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use abideen/starcoder2-chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "abideen/starcoder2-chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "abideen/starcoder2-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/abideen/starcoder2-chat
- SGLang
How to use abideen/starcoder2-chat 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 "abideen/starcoder2-chat" \ --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": "abideen/starcoder2-chat", "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 "abideen/starcoder2-chat" \ --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": "abideen/starcoder2-chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use abideen/starcoder2-chat with Docker Model Runner:
docker model run hf.co/abideen/starcoder2-chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,8 @@ Starcoder-2-chat is an instruction fine-tuned of [bigcode/starcoder2-7b](https:/
|
|
| 24 |
|
| 25 |
## 🏆 Evaluation results
|
| 26 |
|
|
|
|
|
|
|
| 27 |
### HUMANEVAL
|
| 28 |
0.3231707317073171
|
| 29 |
|
|
|
|
| 24 |
|
| 25 |
## 🏆 Evaluation results
|
| 26 |
|
| 27 |
+
Thanks to [Muhammad Bin Usman](https://www.linkedin.com/in/muhammad-bin-usman/) for running evals on Starcoder2-chat.
|
| 28 |
+
|
| 29 |
### HUMANEVAL
|
| 30 |
0.3231707317073171
|
| 31 |
|