Instructions to use felcas93/starcoder2-7b-lora-vpc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use felcas93/starcoder2-7b-lora-vpc with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-7b")
model = PeftModel.from_pretrained(base_model, "felcas93/starcoder2-7b-lora-vpc")

Transformers

How to use felcas93/starcoder2-7b-lora-vpc with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="felcas93/starcoder2-7b-lora-vpc")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("felcas93/starcoder2-7b-lora-vpc", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use felcas93/starcoder2-7b-lora-vpc with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "felcas93/starcoder2-7b-lora-vpc"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "felcas93/starcoder2-7b-lora-vpc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/felcas93/starcoder2-7b-lora-vpc

SGLang

How to use felcas93/starcoder2-7b-lora-vpc 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 "felcas93/starcoder2-7b-lora-vpc" \
    --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": "felcas93/starcoder2-7b-lora-vpc",
		"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 "felcas93/starcoder2-7b-lora-vpc" \
        --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": "felcas93/starcoder2-7b-lora-vpc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use felcas93/starcoder2-7b-lora-vpc with Docker Model Runner:
```
docker model run hf.co/felcas93/starcoder2-7b-lora-vpc
```

Model Card for starcoder2_7b_lora_vpc

This model is a fine-tuned version of bigcode/starcoder2-7b. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

PEFT 0.18.0
TRL: 0.25.1
Transformers: 4.57.3
Pytorch: 2.8.0+cu128
Datasets: 4.4.1
Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 1

Model tree for felcas93/starcoder2-7b-lora-vpc

Base model

bigcode/starcoder2-7b

Adapter

(22)

this model