Text Generation
Transformers
Safetensors
starcoder2
code
Eval Results (legacy)
text-generation-inference
Instructions to use bigcode/starcoder2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigcode/starcoder2-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigcode/starcoder2-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigcode/starcoder2-7b") model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigcode/starcoder2-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigcode/starcoder2-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigcode/starcoder2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigcode/starcoder2-7b
- SGLang
How to use bigcode/starcoder2-7b 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/starcoder2-7b" \ --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/starcoder2-7b", "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/starcoder2-7b" \ --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/starcoder2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigcode/starcoder2-7b with Docker Model Runner:
docker model run hf.co/bigcode/starcoder2-7b
Upload starcoder2-main.zip
#21 opened 6 months ago
by
Pe-pe-lu-69
starcoder2-7b-barth
#20 opened 10 months ago
by
rockson8
Is it possible to use Starcoder2 in llmstudio?
#19 opened about 1 year ago
by
silentstormzc
Enable for AutoTrain?
#18 opened over 1 year ago
by
neighborwang
Chat tempalte for vllm/ aphrodite-engine?
#17 opened over 1 year ago
by
MavWolverine
BirdMan
#16 opened over 1 year ago
by
Birdmanphil
Support inference API for 7b model?
#14 opened almost 2 years ago
by
wmedrano
How to setup Anything LLM to use Inference API (serverless)
1
#13 opened almost 2 years ago
by
Lbenj
fine tuning template
#12 opened about 2 years ago
by
urizlo
Adding Evaluation Results
#11 opened about 2 years ago
by
leaderboard-pr-bot
update readme
#10 opened about 2 years ago
by
ZennyKenny
support relative links with anchors
1
#9 opened about 2 years ago
by
ZennyKenny
Wrong EOS in the generation config?
#8 opened about 2 years ago
by
urikz
its an base model or sft instruction model?
#6 opened about 2 years ago
by
okcwang
Update config.json
#5 opened about 2 years ago
by
muhtasham
What Languages?
2
#3 opened about 2 years ago
by
DaveW111
Hi, will there be an instruction version of the coding model in the future?
👍 8
#2 opened about 2 years ago
by
win10