Instructions to use Kaustubh651/training_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kaustubh651/training_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kaustubh651/training_model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Kaustubh651/training_model") model = AutoModelForCausalLM.from_pretrained("Kaustubh651/training_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kaustubh651/training_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kaustubh651/training_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kaustubh651/training_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Kaustubh651/training_model
- SGLang
How to use Kaustubh651/training_model 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 "Kaustubh651/training_model" \ --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": "Kaustubh651/training_model", "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 "Kaustubh651/training_model" \ --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": "Kaustubh651/training_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Kaustubh651/training_model with Docker Model Runner:
docker model run hf.co/Kaustubh651/training_model
Commit History
-
Upload tokenizer
86b4dfc -
Upload OPTForCausalLM
786acf5 -
Upload tokenizer
82f3b6c -
Upload OPTForCausalLM
9f9b2f3 -
Upload tokenizer
7ab44bf -
Training in progress, step 10000
9d27799 -
Training in progress, step 9500
827341d -
Training in progress, step 9000
933d101 -
Training in progress, step 8500
35401f4 -
Training in progress, step 8000
b1b73c5 -
Training in progress, step 7500
f83a231 -
Training in progress, step 7000
2ae011b -
Training in progress, step 6500
12746de -
Training in progress, step 6000
bcf1bba -
Training in progress, step 5500
cd848f5 -
Training in progress, step 5000
2481680 -
Training in progress, step 4500
0483d33 -
Training in progress, step 4000
b2a5d4b -
Training in progress, step 3500
1425a11 -
Training in progress, step 3000
740bf78 -
Training in progress, step 2500
7b84a52 -
Training in progress, step 2000
d3eba49 -
Training in progress, step 1500
aa56c78 -
Training in progress, step 1000
2d052da -
Training in progress, step 500
1aa2010 -
initial commit
c22cfae