Text Generation
Transformers
Safetensors
metis16
metis
post-trained
instruction-tuned
reasoning
mixture-of-experts
mamba
conversational
custom_code
Instructions to use Lernex/Metis-1.6-Logos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lernex/Metis-1.6-Logos with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Lernex/Metis-1.6-Logos", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Lernex/Metis-1.6-Logos", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Lernex/Metis-1.6-Logos with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Lernex/Metis-1.6-Logos" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lernex/Metis-1.6-Logos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Lernex/Metis-1.6-Logos
- SGLang
How to use Lernex/Metis-1.6-Logos 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 "Lernex/Metis-1.6-Logos" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lernex/Metis-1.6-Logos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Lernex/Metis-1.6-Logos" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lernex/Metis-1.6-Logos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Lernex/Metis-1.6-Logos with Docker Model Runner:
docker model run hf.co/Lernex/Metis-1.6-Logos
Release card
#1
by GiuliannoV - opened
4,981 hidden commits · view all commits
The release card for launch, rebuilt around this repository’s live benchmark table (the table block is carried over verbatim).
- Banner and links row (technical report, collection, Lernex, X, founder)
- Abstract, then the benchmark table first, then the Pareto-frontier and mathematics charts
- Run it: a hardware picker, then Transformers, vLLM (vllm-metis), SGLang (sglang-metis), llama.cpp (PR #31134 until it merges) and MLX
- Architecture figure (the technical report’s, drawn for this model), training lineage, limitations, why Metis, citation
Merge only after the live card updater has stopped: it regenerates README.md from its own template about once a minute and would overwrite this. Rebuild from the final table first (build_cards.py on the server) if the table changed since this PR.
Landed on main as da1fae89.
GiuliannoV changed pull request status to closed