Instructions to use HappyBulingling/MyModel-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HappyBulingling/MyModel-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HappyBulingling/MyModel-sft", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("HappyBulingling/MyModel-sft", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HappyBulingling/MyModel-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HappyBulingling/MyModel-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HappyBulingling/MyModel-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/HappyBulingling/MyModel-sft
- SGLang
How to use HappyBulingling/MyModel-sft 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 "HappyBulingling/MyModel-sft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HappyBulingling/MyModel-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "HappyBulingling/MyModel-sft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HappyBulingling/MyModel-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use HappyBulingling/MyModel-sft with Docker Model Runner:
docker model run hf.co/HappyBulingling/MyModel-sft
Download config.json from HappyBulingling/MyModel-sft: direct link, hf CLI and curl.
- Browser
- Download file 847 Bytes
-
https://huggingface.co/HappyBulingling/MyModel-sft/resolve/main/config.json
- Command line
-
hf download hf://HappyBulingling/MyModel-sft/config.json
-
curl -L -o config.json https://huggingface.co/HappyBulingling/MyModel-sft/resolve/main/config.json
847 Bytes
| { | |
| "architectures": [ | |
| "MyModelForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "auto_map": { | |
| "AutoConfig": "config.MyModelConfig", | |
| "AutoModelForCausalLM": "model.MyModelForCausalLM" | |
| }, | |
| "bos_token_id": 2, | |
| "dropout": 0.0, | |
| "dtype": "float32", | |
| "eos_token_id": 0, | |
| "ffn_type": "dense", | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "im_end_token_id": 5, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2816, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "mymodel", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 20, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 1, | |
| "parametrization": "standard", | |
| "qk_norm": true, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "transformers_version": "4.57.6", | |
| "unk_token_id": 3, | |
| "vocab_size": 32768 | |
| } | |