Text Generation
Transformers
Safetensors
English
llama
600B
Python
Code
Logical Understanding
Relation Establishment
Translation
ai1
DEEPNIGHT
text-generation-inference
Instructions to use deepnight-research/ai1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepnight-research/ai1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="deepnight-research/ai1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("deepnight-research/ai1") model = AutoModelForCausalLM.from_pretrained("deepnight-research/ai1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use deepnight-research/ai1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepnight-research/ai1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepnight-research/ai1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/deepnight-research/ai1
- SGLang
How to use deepnight-research/ai1 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 "deepnight-research/ai1" \ --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": "deepnight-research/ai1", "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 "deepnight-research/ai1" \ --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": "deepnight-research/ai1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use deepnight-research/ai1 with Docker Model Runner:
docker model run hf.co/deepnight-research/ai1
Gated model You can list files but not access them
Preview of files found in this repository
- 1.52 kB
- 0 Bytes
- 2.89 kB
- 676 Bytes
- 963 kB
- 9.66 GB xet
- 10 GB xet
- 11.5 GB xet
- 16.5 GB xet
- 9.97 GB xet
- 9.93 GB xet
- 9.66 GB xet
- 9.93 GB xet
- 13.6 GB xet
- 15.4 GB xet
- 9.68 GB xet
- 9.66 GB xet
- 9.66 GB xet
- 9.93 GB xet
- 13.1 GB xet
- 16.5 GB xet
- 9.66 GB xet
- 10 GB xet
- 9.6 GB xet
- 9.66 GB xet
- 12.4 GB xet
- 16.8 GB xet
- 9.66 GB xet
- 9.66 GB xet
- 9.93 GB xet
- 9.66 GB xet
- 12.4 GB xet
- 16.5 GB xet
- 9.66 GB xet
- 9.66 GB xet
- 9.66 GB xet
- 9.93 GB xet
- 12.4 GB xet
- 16.5 GB xet
- 9.68 GB xet
- 9.66 GB xet
- 9.66 GB xet
- 10 GB xet
- 11.5 GB xet
- 17.7 GB xet
- 9.97 GB xet
- 9.66 GB xet
- 9.93 GB xet
- 9.66 GB xet
- 12.3 GB xet