Instructions to use abhinavp/checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abhinavp/checkpoints with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="abhinavp/checkpoints")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("abhinavp/checkpoints") model = AutoModelForCausalLM.from_pretrained("abhinavp/checkpoints", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use abhinavp/checkpoints with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "abhinavp/checkpoints" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "abhinavp/checkpoints", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/abhinavp/checkpoints
- SGLang
How to use abhinavp/checkpoints 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 "abhinavp/checkpoints" \ --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": "abhinavp/checkpoints", "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 "abhinavp/checkpoints" \ --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": "abhinavp/checkpoints", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use abhinavp/checkpoints with Docker Model Runner:
docker model run hf.co/abhinavp/checkpoints
Download checkpoint-60/pytorch_model.bin from abhinavp/checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 269 MB
-
https://huggingface.co/abhinavp/checkpoints/resolve/main/checkpoint-60/pytorch_model.bin
- Command line
-
hf download hf://abhinavp/checkpoints/checkpoint-60/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/abhinavp/checkpoints/resolve/main/checkpoint-60/pytorch_model.bin
269 MB
- Xet hash:
- 81418dcc190e25c7733c821ef334610ef093ba8f3ee2de280d36a6cf80250500
- Size of remote file:
- 269 MB
- SHA256:
- 570c80bdf2ce4e29833c9d9e58e776f97095f2761633b5446fd8f404ccda8c97
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.