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

gftd
/
gftd-260206

Text Generation
MLX
Safetensors
English
qwen3
apple-silicon
qlora
gftd
knowledge-distillation
Model card Files Files and versions
xet
Community

Instructions to use gftd/gftd-260206 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use gftd/gftd-260206 with MLX:

    # Make sure mlx-lm is installed
    # pip install --upgrade mlx-lm
    # if on a CUDA device, also pip install mlx[cuda]
    
    # Generate text with mlx-lm
    from mlx_lm import load, generate
    
    model, tokenizer = load("gftd/gftd-260206")
    
    prompt = "Once upon a time in"
    text = generate(model, tokenizer, prompt=prompt, verbose=True)
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • LM Studio
  • MLX LM

    How to use gftd/gftd-260206 with MLX LM:

    Generate or start a chat session
    # Install MLX LM
    uv tool install mlx-lm
    # Generate some text
    mlx_lm.generate --model "gftd/gftd-260206" --prompt "Once upon a time"
gftd-260206
17.6 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
com-junkawasaki's picture
com-junkawasaki
Update README.md
e4f590b verified 3 months ago
  • .gitattributes
    1.57 kB
    gftd-distill verify verify-1770368381 3 months ago
  • README.md
    5.84 kB
    Update README.md 3 months ago
  • config.json
    818 Bytes
    Qwen3-8B distilled from Opus 4.6 (200 iters, 100 samples, loss=0.182) 3 months ago
  • generation_config.json
    239 Bytes
    gftd-distill verify verify-1770368381 3 months ago
  • model-00001-of-00004.safetensors
    5.29 GB
    xet
    Qwen3-8B distilled from Opus 4.6 (200 iters, 100 samples, loss=0.182) 3 months ago
  • model-00002-of-00004.safetensors
    5.3 GB
    xet
    Qwen3-8B distilled from Opus 4.6 (200 iters, 100 samples, loss=0.182) 3 months ago
  • model-00003-of-00004.safetensors
    4.55 GB
    xet
    Qwen3-8B distilled from Opus 4.6 (200 iters, 100 samples, loss=0.182) 3 months ago
  • model-00004-of-00004.safetensors
    1.24 GB
    xet
    Qwen3-8B distilled from Opus 4.6 (200 iters, 100 samples, loss=0.182) 3 months ago
  • model.safetensors
    1.19 GB
    xet
    Qwen3-8B distilled from Opus 4.6 (200 iters, 100 samples, loss=0.182) 3 months ago
  • model.safetensors.index.json
    34.5 kB
    Qwen3-8B distilled from Opus 4.6 (200 iters, 100 samples, loss=0.182) 3 months ago
  • tokenizer.json
    11.4 MB
    xet
    gftd-distill verify verify-1770368381 3 months ago
  • tokenizer_config.json
    700 Bytes
    gftd-distill verify verify-1770368381 3 months ago