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

  • Log In
  • Sign Up

darkmaniac7
/
TokForge-AccelerationPack-Draft

Text Generation
English
mnn
speculative-decoding
draft-model
qwen3
tokforge
Model card Files Files and versions
xet
Community
TokForge-AccelerationPack-Draft
338 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
darkmaniac7's picture
darkmaniac7
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
1f8c190 verified 29 days ago
  • .gitattributes
    1.61 kB
    Upload folder using huggingface_hub about 1 month ago
  • README.md
    3.72 kB
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago
  • config.json
    211 Bytes
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago
  • config_cpu.json
    211 Bytes
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago
  • draft_config_cpu.json
    211 Bytes
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago
  • llm.mnn
    504 kB
    xet
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago
  • llm.mnn.weight
    336 MB
    xet
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago
  • llm_config.json
    4.66 kB
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago
  • tokenizer.txt
    1.61 MB
    v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850) 29 days ago