Instructions to use Zenabius/sage-mt5-large-Q6_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zenabius/sage-mt5-large-Q6_K-GGUF with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Zenabius/sage-mt5-large-Q6_K-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Zenabius/sage-mt5-large-Q6_K-GGUF 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 Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K

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 Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K

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 Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K

Use Docker

docker model run hf.co/Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K

LM Studio
Jan
Ollama
How to use Zenabius/sage-mt5-large-Q6_K-GGUF with Ollama:
```
ollama run hf.co/Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K
```
Unsloth Desktop
Docker Model Runner
How to use Zenabius/sage-mt5-large-Q6_K-GGUF with Docker Model Runner:
```
docker model run hf.co/Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K
```

Lemonade

How to use Zenabius/sage-mt5-large-Q6_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Zenabius/sage-mt5-large-Q6_K-GGUF:Q6_K

Run and chat with the model

lemonade run user.sage-mt5-large-Q6_K-GGUF-Q6_K

List all available models

lemonade list

Atomic Chat

sage-mt5-large-Q6_K-GGUF / README.md

Zenabius

Upload README.md with huggingface_hub

9524a46 verified 12 months ago

preview code

Raw History Blame Contribute Delete

3.6 kB

metadata

language:
  - ru
  - en
tags:
  - spellchecking
  - pytorch
  - natural language generation
  - llama-cpp
  - gguf-my-repo
license: mit
metrics:
  - precision
  - recall
  - f1
library_name: transformers
base_model: ai-forever/sage-mt5-large
model-index:
  - name: sage-mt5-large
    results:
      - task:
          type: text-generation
        dataset:
          name: RUSpellRU
          type: spellcheck_benchmark
        metrics:
          - type: precision
            value: 55.7
            name: Precision
            verified: false
          - type: recall
            value: 68.5
            name: Recall
            verified: false
          - type: f1
            value: 61.4
            name: F1
            verified: false
          - type: precision
            value: 35.4
            name: Precision
            verified: false
          - type: recall
            value: 57.9
            name: Recall
            verified: false
          - type: f1
            value: 43.9
            name: F1
            verified: false
          - type: precision
            value: 35.1
            name: Precision
            verified: false
          - type: recall
            value: 70.8
            name: Recall
            verified: false
          - type: f1
            value: 47
            name: F1
            verified: false
          - type: precision
            value: 47.4
            name: Precision
            verified: false
          - type: recall
            value: 53.8
            name: Recall
            verified: false
          - type: f1
            value: 50.4
            name: F1
            verified: false
      - task:
          type: text-generation
        dataset:
          name: JFLEG
          type: JFLEG
        metrics:
          - type: precision
            value: 74.9
            name: Precision
            verified: false
          - type: recall
            value: 88.4
            name: Recall
            verified: false
          - type: f1
            value: 81.1
            name: F1
            verified: false
      - task:
          type: text-generation
        dataset:
          name: BEA60K
          type: bea60k
        metrics:
          - type: precision
            value: 64.7
            name: Precision
            verified: false
          - type: recall
            value: 83.8
            name: Recall
            verified: false
          - type: f1
            value: 73
            name: F1
            verified: false

Zenabius/sage-mt5-large-Q6_K-GGUF

This model was converted to GGUF format from ai-forever/sage-mt5-large using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Zenabius/sage-mt5-large-Q6_K-GGUF --hf-file sage-mt5-large-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Zenabius/sage-mt5-large-Q6_K-GGUF --hf-file sage-mt5-large-q6_k.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Zenabius/sage-mt5-large-Q6_K-GGUF --hf-file sage-mt5-large-q6_k.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo Zenabius/sage-mt5-large-Q6_K-GGUF --hf-file sage-mt5-large-q6_k.gguf -c 2048