Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Lernex
/
Metis-1.5-base

Text Generation
Safetensors
JAX
English
metis_multihead_latent_moe
metis
mixture-of-experts
Mixture of Experts
latent-moe
tpu
pretrained
base-model
conversational
Model card Files Files and versions
xet
Community
Metis-1.5-base
1.8 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
GiuliannoV's picture
GiuliannoV
Add raw eval results
c6ce0c6 verified 19 days ago
  • .gitattributes
    1.52 kB
    initial commit 19 days ago
  • README.md
    13.5 kB
    Add evaluation results (base vs think, full test sets) 19 days ago
  • config.json
    947 Bytes
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago
  • eval_results.json
    2.35 kB
    Add raw eval results 19 days ago
  • export_meta.json
    132 Bytes
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago
  • generation_config.json
    151 Bytes
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago
  • model.safetensors
    1.8 GB
    xet
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago
  • special_tokens_map.json
    99 Bytes
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago
  • tokenizer.json
    2.31 MB
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago
  • tokenizer_config.json
    609 Bytes
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago
  • tokenizer_meta.json
    522 Bytes
    Metis-1.5-base: 898M single-latent MoE, 50B-token JAX/TPU pretrain 19 days ago