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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

TheBlueObserver
/
Meta-Llama-3-8B-MLX

Text Generation
MLX
Safetensors
PyTorch
English
llama
facebook
meta
llama-3
Model card Files Files and versions
xet
Community
1

Instructions to use TheBlueObserver/Meta-Llama-3-8B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use TheBlueObserver/Meta-Llama-3-8B-MLX 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("TheBlueObserver/Meta-Llama-3-8B-MLX")
    
    prompt = "Once upon a time in"
    text = generate(model, tokenizer, prompt=prompt, verbose=True)
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
  • MLX LM

    How to use TheBlueObserver/Meta-Llama-3-8B-MLX with MLX LM:

    Generate or start a chat session
    # Install MLX LM
    uv tool install mlx-lm
    # Generate some text
    mlx_lm.generate --model "TheBlueObserver/Meta-Llama-3-8B-MLX" --prompt "Once upon a time"
  • Atomic Chat
Meta-Llama-3-8B-MLX
16.1 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 5 commits
TheBlueObserver's picture
TheBlueObserver
7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792
bbfc96e verified over 1 year ago
  • .gitattributes
    1.52 kB
    initial commit over 1 year ago
  • README.md
    14.7 kB
    7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792 over 1 year ago
  • config.json
    705 Bytes
    7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792 over 1 year ago
  • model-00001-of-00004.safetensors
    5.3 GB
    xet
    5fd8daf098d1e4d12838d132b7672a03126048029903977d5e102630bb1fd669 over 1 year ago
  • model-00002-of-00004.safetensors
    5.35 GB
    xet
    f2c11b8a4321faa5b5c43df4614ffd6f3cf64b4d3b2c61be9a30be21a888fa3f over 1 year ago
  • model-00003-of-00004.safetensors
    4.36 GB
    xet
    1373b8a0457e2b083d51af6c4c43c59937eb238d818110a7f764e317976568df over 1 year ago
  • model-00004-of-00004.safetensors
    1.05 GB
    xet
    7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792 over 1 year ago
  • model.safetensors.index.json
    25.1 kB
    7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792 over 1 year ago
  • special_tokens_map.json
    301 Bytes
    7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792 over 1 year ago
  • tokenizer.json
    9.09 MB
    7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792 over 1 year ago
  • tokenizer_config.json
    50.6 kB
    7fc93e7ea15144a23b69e877bf011a96e2d5e502a209269e1d0ac20d30553792 over 1 year ago