Text Generation
Transformers
PyTorch
English
gpt_neox
gpt
llm
large language model
h2o-llmstudio
text-generation-inference
Instructions to use Shishir1807/Model_M4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shishir1807/Model_M4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Shishir1807/Model_M4")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Shishir1807/Model_M4") model = AutoModelForCausalLM.from_pretrained("Shishir1807/Model_M4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Shishir1807/Model_M4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Shishir1807/Model_M4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Shishir1807/Model_M4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Shishir1807/Model_M4
- SGLang
How to use Shishir1807/Model_M4 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 "Shishir1807/Model_M4" \ --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": "Shishir1807/Model_M4", "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 "Shishir1807/Model_M4" \ --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": "Shishir1807/Model_M4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Shishir1807/Model_M4 with Docker Model Runner:
docker model run hf.co/Shishir1807/Model_M4
Download pytorch_model.bin from Shishir1807/Model_M4: direct link, hf CLI and curl.
- Browser
- Download file 5.68 GB
-
https://huggingface.co/Shishir1807/Model_M4/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://Shishir1807/Model_M4/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/Shishir1807/Model_M4/resolve/main/pytorch_model.bin
5.68 GB
- Xet hash:
- 48fa3a439bbfa1a12d18bee8775df5636e5903afda3d5bdc617b39249fc1c24e
- Size of remote file:
- 5.68 GB
- SHA256:
- 160713720fb3e10b20150573ce8f9696bd7b5bf42acad16051c0e132de82c5ef
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.