Instructions to use deepaksamuel-cuk/trackfit-llm-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepaksamuel-cuk/trackfit-llm-large with Transformers:

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

pipe = pipeline("text-generation", model="deepaksamuel-cuk/trackfit-llm-large")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepaksamuel-cuk/trackfit-llm-large")
model = AutoModelForCausalLM.from_pretrained("deepaksamuel-cuk/trackfit-llm-large", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepaksamuel-cuk/trackfit-llm-large with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/deepaksamuel-cuk/trackfit-llm-large

SGLang

How to use deepaksamuel-cuk/trackfit-llm-large 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 "deepaksamuel-cuk/trackfit-llm-large" \
    --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": "deepaksamuel-cuk/trackfit-llm-large",
		"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 "deepaksamuel-cuk/trackfit-llm-large" \
        --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": "deepaksamuel-cuk/trackfit-llm-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepaksamuel-cuk/trackfit-llm-large with Docker Model Runner:
```
docker model run hf.co/deepaksamuel-cuk/trackfit-llm-large
```

trackfit-llm-large / allowed.csv

deepaksamuel-cuk

Add large extended track-fitting model (epoch 320), tokenizer, helpers, examples and README

bf6ae7d verified 16 days ago

Raw History Contribute Delete

502 kB

File too large to display, you can check the raw version instead.