Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

unconst
/
souped_v2

Safetensors
deepseek_v3
Model card Files Files and versions
xet
Community
souped_v2
31.9 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
unconst's picture
unconst
iter74: add num_local_experts/num_shared_experts aliases (validator MoE accounting)
d216345 verified 1 day ago
  • .gitattributes
    1.57 kB
    iter61 souped_v2 alpha=0.85 (0.85*hope_king + 0.15*new_king) merged via merge_interp.py 1 day ago
  • chat_template.jinja
    4.02 kB
    iter61 souped_v2 alpha=0.85 (0.85*hope_king + 0.15*new_king) merged via merge_interp.py 1 day ago
  • config.json
    1.37 kB
    iter74: add num_local_experts/num_shared_experts aliases (validator MoE accounting) 1 day ago
  • generation_config.json
    146 Bytes
    iter61 souped_v2 alpha=0.85 (0.85*hope_king + 0.15*new_king) merged via merge_interp.py 1 day ago
  • model.safetensors
    31.9 GB
    xet
    iter61 souped_v2 alpha=0.85 (0.85*hope_king + 0.15*new_king) merged via merge_interp.py 1 day ago
  • tiktoken.model
    2.8 MB
    xet
    iter61 souped_v2 alpha=0.85 (0.85*hope_king + 0.15*new_king) merged via merge_interp.py 1 day ago
  • tokenizer.json
    19.5 MB
    xet
    iter61 souped_v2 alpha=0.85 (0.85*hope_king + 0.15*new_king) merged via merge_interp.py 1 day ago
  • tokenizer_config.json
    645 Bytes
    iter61 souped_v2 alpha=0.85 (0.85*hope_king + 0.15*new_king) merged via merge_interp.py 1 day ago