Instructions to use shamsghi/Mistral-Le-Chaton-Fat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shamsghi/Mistral-Le-Chaton-Fat with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("shamsghi/Mistral-Le-Chaton-Fat")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use shamsghi/Mistral-Le-Chaton-Fat with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "shamsghi/Mistral-Le-Chaton-Fat"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "shamsghi/Mistral-Le-Chaton-Fat"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use shamsghi/Mistral-Le-Chaton-Fat with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "shamsghi/Mistral-Le-Chaton-Fat"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default shamsghi/Mistral-Le-Chaton-Fat

Run Hermes

hermes

MLX LM

How to use shamsghi/Mistral-Le-Chaton-Fat with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "shamsghi/Mistral-Le-Chaton-Fat"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "shamsghi/Mistral-Le-Chaton-Fat"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "shamsghi/Mistral-Le-Chaton-Fat",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

shamsghi commited on 14 days ago

Commit

a591a0a

verified ·

1 Parent(s): 7069df4

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

	@@ -22,7 +22,7 @@ Le Chaton Fat is state of the art on nearly all tested benchmarks, with exceptio
22
23
24
25	- Le Chaton Fat launches today alongside Le Chaton Mythique. The two share the same underlying model, but ~~Mythos~~ 5, so far deployed only through Project Glassloaf, has the safeguards lifted in some areas. The safeguards are what distinguish the two, and why we've given them different names.
26
27
28


22
23
24
25	+ Le Chaton Fat launches today alongside Le Chaton Mythique. The two share the same underlying model, but Le Chaton Mythique, so far deployed only through Project Glassloaf, has the safeguards lifted in some areas. The safeguards are what distinguish the two, and why we've given them different names.
26
27
28