Instructions to use unlimitedbytes/gptoss-bigcodebench-20b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unlimitedbytes/gptoss-bigcodebench-20b-lora with Transformers:

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

pipe = pipeline("text-generation", model="unlimitedbytes/gptoss-bigcodebench-20b-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unlimitedbytes/gptoss-bigcodebench-20b-lora", dtype="auto")

PEFT
How to use unlimitedbytes/gptoss-bigcodebench-20b-lora with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unlimitedbytes/gptoss-bigcodebench-20b-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unlimitedbytes/gptoss-bigcodebench-20b-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unlimitedbytes/gptoss-bigcodebench-20b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unlimitedbytes/gptoss-bigcodebench-20b-lora

SGLang

How to use unlimitedbytes/gptoss-bigcodebench-20b-lora 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 "unlimitedbytes/gptoss-bigcodebench-20b-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unlimitedbytes/gptoss-bigcodebench-20b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "unlimitedbytes/gptoss-bigcodebench-20b-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unlimitedbytes/gptoss-bigcodebench-20b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use unlimitedbytes/gptoss-bigcodebench-20b-lora with Docker Model Runner:
```
docker model run hf.co/unlimitedbytes/gptoss-bigcodebench-20b-lora
```

gptoss-bigcodebench-20b-lora / log.jsonl

unlimitedbytes

Upload folder using huggingface_hub

0a2552d verified 10 months ago

raw

history blame contribute delete

1.62 kB

	{"time": 1755040255.0687401, "step": null, "level": "INFO", "msg": "Config loaded", "data": {"config_path": "configs/full.yaml"}}
	{"time": 1755040255.068824, "step": null, "level": "INFO", "msg": "Loading dataset ...", "data": {}}
	{"time": 1755040257.6130784, "step": null, "level": "INFO", "msg": "Dataset loaded", "data": {"size": 2}}
	{"time": 1755040257.6131446, "step": null, "level": "INFO", "msg": "Loading model/tokenizer ...", "data": {}}
	{"time": 1755040264.1002383, "step": null, "level": "INFO", "msg": "Model loaded", "data": {"trainable_params": 15040512}}
	{"time": 1755040264.3870833, "step": null, "level": "INFO", "msg": "Starting training ...", "data": {}}
	{"time": 1755040527.7214618, "step": null, "level": "INFO", "msg": "Config loaded", "data": {"config_path": "configs/full.yaml"}}
	{"time": 1755040527.7215579, "step": null, "level": "INFO", "msg": "Loading dataset ...", "data": {}}
	{"time": 1755040529.3749201, "step": null, "level": "INFO", "msg": "Dataset loaded", "data": {"size": 1140}}
	{"time": 1755040529.3750272, "step": null, "level": "INFO", "msg": "Loading model/tokenizer ...", "data": {}}
	{"time": 1755040535.6129575, "step": null, "level": "INFO", "msg": "Model loaded", "data": {"trainable_params": 15040512}}
	{"time": 1755040536.956728, "step": null, "level": "INFO", "msg": "Starting training ...", "data": {}}
	{"time": 1755044254.8595893, "step": null, "level": "INFO", "msg": "Training complete", "data": {"train_runtime": 3717.3139, "train_samples_per_second": 0.43, "train_steps_per_second": 0.027, "total_flos": 6.825417425085542e+16, "train_loss": 0.7833267974853516}}