Instructions to use MM98/ft-bz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MM98/ft-bz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MM98/ft-bz")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MM98/ft-bz") model = AutoModelForCausalLM.from_pretrained("MM98/ft-bz", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MM98/ft-bz with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MM98/ft-bz" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MM98/ft-bz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MM98/ft-bz
- SGLang
How to use MM98/ft-bz 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 "MM98/ft-bz" \ --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": "MM98/ft-bz", "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 "MM98/ft-bz" \ --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": "MM98/ft-bz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MM98/ft-bz with Docker Model Runner:
docker model run hf.co/MM98/ft-bz
Download config.json from MM98/ft-bz: direct link, hf CLI and curl.
- Browser
- Download file 1.52 kB
-
https://huggingface.co/MM98/ft-bz/resolve/main/config.json
- Command line
-
hf download hf://MM98/ft-bz/config.json
-
curl -L -o config.json https://huggingface.co/MM98/ft-bz/resolve/main/config.json
1.52 kB
| { | |
| "_name_or_path": "parhamabedazad/ft-bz", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_dropout": 0.1, | |
| "attn_pdrop": 0.1, | |
| "beta1": 0.9, | |
| "beta2": 0.98, | |
| "bos_token_id": 8, | |
| "data_path": "", | |
| "embd_pdrop": 0.1, | |
| "embed_dropout": 0.1, | |
| "eos_token_id": 9, | |
| "epsilon": 1e-09, | |
| "eval_batch_size": 128, | |
| "eval_steps": 10, | |
| "gradient_checkpointing": false, | |
| "initializer_range": 0.02, | |
| "iterations": 1000, | |
| "layer_norm_epsilon": 1e-05, | |
| "line_count": 1, | |
| "lr": 0.00025, | |
| "max_steps": 3600000, | |
| "model": "GPT2", | |
| "model_type": "gpt2", | |
| "n_ctx": 256, | |
| "n_embd": 1024, | |
| "n_head": 16, | |
| "n_inner": null, | |
| "n_layer": 24, | |
| "n_positions": 256, | |
| "n_vocab": 25000, | |
| "opt_name": "adam", | |
| "precision": "float32", | |
| "predict_batch_size": 8, | |
| "reorder_and_upcast_attn": false, | |
| "res_dropout": 0.1, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "scale_by_depth": true, | |
| "scale_by_in": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "tokenizer_class": "AlbertTokenizer", | |
| "torch_dtype": "float32", | |
| "train_batch_size": 320, | |
| "train_steps": 10000, | |
| "transformers_version": "4.15.0", | |
| "use_cache": true, | |
| "vocab_size": 25000, | |
| "warmup_steps": 2000, | |
| "weight_decay": 0.01 | |
| } | |