Text Generation
Transformers
PyTorch
private_llm
feature-extraction
custom-code
private-llm
custom_code
Instructions to use MarioBoscoGPU/fqpegaqmsmbd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MarioBoscoGPU/fqpegaqmsmbd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MarioBoscoGPU/fqpegaqmsmbd", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MarioBoscoGPU/fqpegaqmsmbd", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MarioBoscoGPU/fqpegaqmsmbd with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MarioBoscoGPU/fqpegaqmsmbd" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MarioBoscoGPU/fqpegaqmsmbd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MarioBoscoGPU/fqpegaqmsmbd
- SGLang
How to use MarioBoscoGPU/fqpegaqmsmbd 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 "MarioBoscoGPU/fqpegaqmsmbd" \ --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": "MarioBoscoGPU/fqpegaqmsmbd", "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 "MarioBoscoGPU/fqpegaqmsmbd" \ --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": "MarioBoscoGPU/fqpegaqmsmbd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MarioBoscoGPU/fqpegaqmsmbd with Docker Model Runner:
docker model run hf.co/MarioBoscoGPU/fqpegaqmsmbd
| { | |
| "architectures": [ | |
| "PrivateLLMForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_private_llm.PrivateLLMConfig", | |
| "AutoModel": "modeling_private_llm.PrivateLLMForCausalLM", | |
| "AutoModelForCausalLM": "modeling_private_llm.PrivateLLMForCausalLM", | |
| "AutoTokenizer": [ | |
| "tokenization_private_llm.PrivateLLMTokenizer", | |
| null | |
| ] | |
| }, | |
| "bos_token_id": 258, | |
| "custom_pipelines": { | |
| "private-llm": { | |
| "impl": "pipeline_private_llm.PrivateLLMPipeline", | |
| "pt": [ | |
| "AutoModelForCausalLM" | |
| ] | |
| } | |
| }, | |
| "eos_token_id": 257, | |
| "execution_mode": "auto", | |
| "generate_function": null, | |
| "init_kwargs": {}, | |
| "loader_function": null, | |
| "model_class": null, | |
| "model_type": "private_llm", | |
| "pad_token_id": 256, | |
| "private_output_includes_prompt": false, | |
| "private_script": "private_LLM_model.py", | |
| "subprocess_args": [], | |
| "subprocess_prompt_mode": "stdin", | |
| "subprocess_timeout": 300, | |
| "tokenizer_class": "PrivateLLMTokenizer", | |
| "tokenizer_vocab_file": "private_llm_tokenizer.json", | |
| "torch_dtype": "float32", | |
| "vocab_size": 260 | |
| } | |