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-Praxis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lernex/Metis-1.6-Praxis with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Lernex/Metis-1.6-Praxis", 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-Praxis", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Lernex/Metis-1.6-Praxis 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-Praxis" # 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-Praxis", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Lernex/Metis-1.6-Praxis
- SGLang
How to use Lernex/Metis-1.6-Praxis 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-Praxis" \ --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-Praxis", "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-Praxis" \ --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-Praxis", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Lernex/Metis-1.6-Praxis with Docker Model Runner:
docker model run hf.co/Lernex/Metis-1.6-Praxis
Download config.json from Lernex/Metis-1.6-Praxis: direct link, hf CLI and curl.
- Browser
- Download file 1.27 kB
-
https://huggingface.co/Lernex/Metis-1.6-Praxis/resolve/main/config.json
- Command line
-
hf download hf://Lernex/Metis-1.6-Praxis/config.json
-
curl -L -o config.json https://huggingface.co/Lernex/Metis-1.6-Praxis/resolve/main/config.json
1.27 kB
| { | |
| "architectures": [ | |
| "Metis16ForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_metis16.Metis16Config", | |
| "AutoModelForCausalLM": "modeling_metis16.Metis16ForCausalLM" | |
| }, | |
| "model_type": "metis16", | |
| "family": "praxis", | |
| "vocab_size": 65536, | |
| "hidden_size": 2048, | |
| "num_hidden_layers": 12, | |
| "attention_layer_indices": [ | |
| 4, | |
| 8 | |
| ], | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 8, | |
| "head_dim": 64, | |
| "attention_pass_lora_rank": 8, | |
| "mamba_d_state": 128, | |
| "mamba_d_conv": 4, | |
| "mamba_expand": 2, | |
| "mamba_head_dim": 64, | |
| "mamba_n_groups": 8, | |
| "mamba_chunk_size": 256, | |
| "mamba_norm_eps": 1e-05, | |
| "n_streams": 4, | |
| "mhc_pass_embedding_dim": 64, | |
| "mhc_sinkhorn_iterations": 8, | |
| "latent_dim": 1024, | |
| "n_routed_experts": 128, | |
| "num_experts_per_tok": 4, | |
| "min_routed_k": 1, | |
| "max_routed_k": 8, | |
| "expert_intermediate_size": 512, | |
| "shared_expert_intermediate_size": 512, | |
| "route_feature_dim": 256, | |
| "memory_dim": 256, | |
| "num_passes": 2, | |
| "max_passes": 5, | |
| "continuation_logit_limit": 4.0, | |
| "rms_norm_eps": 1e-06, | |
| "max_position_embeddings": 131072, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "pad_token_id": 1, | |
| "bos_token_id": null, | |
| "eos_token_id": [ | |
| 4, | |
| 0 | |
| ], | |
| "torch_dtype": "bfloat16" | |
| } | |