Instructions to use LoSboccacc/ThinkExtension-4x7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoSboccacc/ThinkExtension-4x7 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LoSboccacc/ThinkExtension-4x7",
	filename="ThinkExtension-4x7.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LoSboccacc/ThinkExtension-4x7 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LoSboccacc/ThinkExtension-4x7:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LoSboccacc/ThinkExtension-4x7:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LoSboccacc/ThinkExtension-4x7:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LoSboccacc/ThinkExtension-4x7: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 LoSboccacc/ThinkExtension-4x7:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LoSboccacc/ThinkExtension-4x7: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 LoSboccacc/ThinkExtension-4x7:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LoSboccacc/ThinkExtension-4x7:Q4_K_M

Use Docker

docker model run hf.co/LoSboccacc/ThinkExtension-4x7:Q4_K_M

LM Studio
Jan
Ollama
How to use LoSboccacc/ThinkExtension-4x7 with Ollama:
```
ollama run hf.co/LoSboccacc/ThinkExtension-4x7:Q4_K_M
```

Unsloth Studio new

How to use LoSboccacc/ThinkExtension-4x7 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 LoSboccacc/ThinkExtension-4x7 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 LoSboccacc/ThinkExtension-4x7 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LoSboccacc/ThinkExtension-4x7 to start chatting

Docker Model Runner
How to use LoSboccacc/ThinkExtension-4x7 with Docker Model Runner:
```
docker model run hf.co/LoSboccacc/ThinkExtension-4x7:Q4_K_M
```

Lemonade

How to use LoSboccacc/ThinkExtension-4x7 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LoSboccacc/ThinkExtension-4x7:Q4_K_M

Run and chat with the model

lemonade run user.ThinkExtension-4x7-Q4_K_M

List all available models

lemonade list

MOE with Mergekit/Mixtral:

    base_model: mistralai/Mistral-7B-Instruct-v0.2
    gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
    dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
    experts:
      - source_model: SanjiWatsuki/Silicon-Maid-7B
        positive_prompts:
          - "roleplay"
          - "story telling"
          - "fantasy"
          - "dreaming"
      - source_model: teknium/OpenHermes-2.5-Mistral-7B
        positive_prompts:
          - "chat"
          - "flow chart"
          - "diagrams"
          - "reasoning"
          - "explanation"
      - source_model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft
        positive_prompts:
          - "programming"
          - "code debugging"
          - "data transformation"
          - "data structures"
        negative_prompt:
          - "chat"
      - source_model: meta-math/MetaMath-Mistral-7B
        positive_prompts:
          - "math"
          - "arithmetic"
          - "algebra"

chatml prompt

Downloads last month: 12

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support