Instructions to use BICORP/Lake-1-6B-spe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BICORP/Lake-1-6B-spe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BICORP/Lake-1-6B-spe")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BICORP/Lake-1-6B-spe") model = AutoModelForCausalLM.from_pretrained("BICORP/Lake-1-6B-spe") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BICORP/Lake-1-6B-spe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BICORP/Lake-1-6B-spe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BICORP/Lake-1-6B-spe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BICORP/Lake-1-6B-spe
- SGLang
How to use BICORP/Lake-1-6B-spe 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 "BICORP/Lake-1-6B-spe" \ --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": "BICORP/Lake-1-6B-spe", "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 "BICORP/Lake-1-6B-spe" \ --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": "BICORP/Lake-1-6B-spe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BICORP/Lake-1-6B-spe with Docker Model Runner:
docker model run hf.co/BICORP/Lake-1-6B-spe
Model Card for Model ID
This modelcard aims to be a base template for new models. It has been generated using this raw template.
Model Details
Model Description
- Developed by: [BI Corp]
- Funded by: [BI Corp]
- Shared by: [BI Corp]
- Model type: [NLP Self-Training Transformers (with pytorch)]
- Language(s) (NLP): [English, Russsian]
- License: [MIT]
- Finetuned from models: [Qwen 2.5 7b, Llama 3.1 3b.]
Training Hyperparameters
- Training regime: [bf16 mixed precision]
- Downloads last month
- 5