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

cnuland
/
legunas21-custom

GGUF
laguna
llama.cpp
vulkan
amd
strix-halo
dflash
speculative-decoding
openshift
conversational
Model card Files Files and versions
xet
Community

Instructions to use cnuland/legunas21-custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • llama.cpp

    How to use cnuland/legunas21-custom with llama.cpp:

    Install (macOS, Linux)
    curl -LsSf https://llama.app/install.sh | sh
    # Start a local OpenAI-compatible server with a web UI:
    llama serve -hf cnuland/legunas21-custom:Q4_K_M
    # Run inference directly in the terminal:
    llama cli -hf cnuland/legunas21-custom:Q4_K_M
    Install from WinGet (Windows)
    winget install llama.cpp
    # Start a local OpenAI-compatible server with a web UI:
    llama serve -hf cnuland/legunas21-custom:Q4_K_M
    # Run inference directly in the terminal:
    llama cli -hf cnuland/legunas21-custom:Q4_K_M
    Use pre-built binary
    # Download pre-built binary from:
    # https://github.com/ggerganov/llama.cpp/releases
    # Start a local OpenAI-compatible server with a web UI:
    ./llama-server -hf cnuland/legunas21-custom:Q4_K_M
    # Run inference directly in the terminal:
    ./llama-cli -hf cnuland/legunas21-custom:Q4_K_M
    Build from source code
    git clone https://github.com/ggerganov/llama.cpp.git
    cd llama.cpp
    cmake -B build
    cmake --build build -j --target llama-server llama-cli
    # Start a local OpenAI-compatible server with a web UI:
    ./build/bin/llama-server -hf cnuland/legunas21-custom:Q4_K_M
    # Run inference directly in the terminal:
    ./build/bin/llama-cli -hf cnuland/legunas21-custom:Q4_K_M
    Use Docker
    docker model run hf.co/cnuland/legunas21-custom:Q4_K_M
  • LM Studio
  • Jan
  • Ollama

    How to use cnuland/legunas21-custom with Ollama:

    ollama run hf.co/cnuland/legunas21-custom:Q4_K_M
  • Unsloth Studio

    How to use cnuland/legunas21-custom with Unsloth Studio:

    Install Unsloth Studio (macOS, Linux, WSL)
    curl -fsSL https://unsloth.ai/install.sh | sh
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for cnuland/legunas21-custom to start chatting
    Install Unsloth Studio (Windows)
    irm https://unsloth.ai/install.ps1 | iex
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for cnuland/legunas21-custom to start chatting
    Using HuggingFace Spaces for Unsloth
    # No setup required
    # Open https://huggingface.co/spaces/unsloth/studio in your browser
    # Search for cnuland/legunas21-custom to start chatting
  • Atomic Chat new
  • Docker Model Runner

    How to use cnuland/legunas21-custom with Docker Model Runner:

    docker model run hf.co/cnuland/legunas21-custom:Q4_K_M
  • Lemonade

    How to use cnuland/legunas21-custom with Lemonade:

    Pull the model
    # Download Lemonade from https://lemonade-server.ai/
    lemonade pull cnuland/legunas21-custom:Q4_K_M
    Run and chat with the model
    lemonade run user.legunas21-custom-Q4_K_M
    List all available models
    lemonade list
legunas21-custom
652 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
cnuland's picture
cnuland
Fix DFlash draft: requant from post-fix BF16 (adds sliding_window metadata); APEX i-compact results; remove broken pre-fix draft mirrors
7a0c0f8 verified 9 days ago
  • .gitattributes
    1.74 kB
    Fix DFlash draft: requant from post-fix BF16 (adds sliding_window metadata); APEX i-compact results; remove broken pre-fix draft mirrors 9 days ago
  • README.md
    6.01 kB
    Fix DFlash draft: requant from post-fix BF16 (adds sliding_window metadata); APEX i-compact results; remove broken pre-fix draft mirrors 9 days ago
  • bench_laguna.py
    1.94 kB
    Upload folder using huggingface_hub 9 days ago
  • deployment.yaml
    3.31 kB
    Upload folder using huggingface_hub 9 days ago
  • laguna-s-2.1-DFlash-Q4_K_M-fixed.gguf
    652 MB
    xet
    Fix DFlash draft: requant from post-fix BF16 (adds sliding_window metadata); APEX i-compact results; remove broken pre-fix draft mirrors 9 days ago
  • speculative-cmath.patch
    136 Bytes
    Upload folder using huggingface_hub 9 days ago