Instructions to use OpenNLG/OpenBA-V1-Based with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenNLG/OpenBA-V1-Based with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenNLG/OpenBA-V1-Based", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenNLG/OpenBA-V1-Based", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use OpenNLG/OpenBA-V1-Based with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenNLG/OpenBA-V1-Based" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenNLG/OpenBA-V1-Based", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OpenNLG/OpenBA-V1-Based
- SGLang
How to use OpenNLG/OpenBA-V1-Based 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 "OpenNLG/OpenBA-V1-Based" \ --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": "OpenNLG/OpenBA-V1-Based", "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 "OpenNLG/OpenBA-V1-Based" \ --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": "OpenNLG/OpenBA-V1-Based", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OpenNLG/OpenBA-V1-Based with Docker Model Runner:
docker model run hf.co/OpenNLG/OpenBA-V1-Based
| { | |
| "add_ffn_bias": false, | |
| "add_lm_head_bias": true, | |
| "add_qkv_bias": true, | |
| "architectures": [ | |
| "OpenBAForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_openba.OpenBAConfig", | |
| "AutoModel": "modeling_openba.OpenBAForConditionalGeneration", | |
| "AutoModelForCausalLM": "modeling_openba.OpenBAForConditionalGeneration", | |
| "AutoModelForSeq2SeqLM": "modeling_openba.OpenBAForConditionalGeneration" | |
| }, | |
| "attention_dropout": 0.1, | |
| "decoder_max_seq_length": 1024, | |
| "decoder_start_token_id": 0, | |
| "eos_token_id": 1, | |
| "ffn_hidden_size": 16384, | |
| "hidden_dropout": 0.1, | |
| "hidden_size": 4096, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "kv_channels": 128, | |
| "max_seq_length": 1024, | |
| "model_type": "openba", | |
| "num_decoder_layers": 36, | |
| "num_heads": 40, | |
| "num_layers": 12, | |
| "pad_token_id": 0, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "OpenBATokenizer", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "vocab_size": 250368 | |
| } | |