Instructions to use dataautogpt3/miqu-120b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dataautogpt3/miqu-120b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dataautogpt3/miqu-120b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dataautogpt3/miqu-120b") model = AutoModelForCausalLM.from_pretrained("dataautogpt3/miqu-120b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dataautogpt3/miqu-120b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dataautogpt3/miqu-120b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dataautogpt3/miqu-120b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dataautogpt3/miqu-120b
- SGLang
How to use dataautogpt3/miqu-120b 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 "dataautogpt3/miqu-120b" \ --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": "dataautogpt3/miqu-120b", "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 "dataautogpt3/miqu-120b" \ --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": "dataautogpt3/miqu-120b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dataautogpt3/miqu-120b with Docker Model Runner:
docker model run hf.co/dataautogpt3/miqu-120b
Is this even good?
#1
by nonetrix - opened
A frankenstein merge but it's just the model duplicated? Is it even better than the normal 70B? Wouldn't it be better to merge with another smart 70B model?
It does not make sense to me either, and I have testing lots of different possibilities of doing self-merges. In addition, this is not 120b, but 140b instead.