Instructions to use Open-Foundation-Models/PolyNorm_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Open-Foundation-Models/PolyNorm_1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Open-Foundation-Models/PolyNorm_1B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Open-Foundation-Models/PolyNorm_1B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Open-Foundation-Models/PolyNorm_1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Open-Foundation-Models/PolyNorm_1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Open-Foundation-Models/PolyNorm_1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Open-Foundation-Models/PolyNorm_1B
- SGLang
How to use Open-Foundation-Models/PolyNorm_1B 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 "Open-Foundation-Models/PolyNorm_1B" \ --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": "Open-Foundation-Models/PolyNorm_1B", "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 "Open-Foundation-Models/PolyNorm_1B" \ --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": "Open-Foundation-Models/PolyNorm_1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Open-Foundation-Models/PolyNorm_1B with Docker Model Runner:
docker model run hf.co/Open-Foundation-Models/PolyNorm_1B
| { | |
| "architectures": [ | |
| "PolyLLaMAForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_polyllama.PolyLlamaConfig", | |
| "AutoModel": "modeling_polyllama.PolyLlamaForCausalLM", | |
| "AutoModelForCausalLM": "modeling_polyllama.PolyLlamaForCausalLM" | |
| }, | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "hidden_act": "PolyNorm", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8256, | |
| "max_position_embeddings": 4096, | |
| "max_sequence_length": 4096, | |
| "model_type": "polyllama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.34.1", | |
| "use_cache": true, | |
| "vocab_size": 32001 | |
| } | |