Instructions to use vasanth009/LC-350M-light with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vasanth009/LC-350M-light 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("vasanth009/LC-350M-light")

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 vasanth009/LC-350M-light with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "vasanth009/LC-350M-light"

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": "vasanth009/LC-350M-light"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vasanth009/LC-350M-light 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 "vasanth009/LC-350M-light"

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 vasanth009/LC-350M-light

Run Hermes

hermes

OpenClaw new

How to use vasanth009/LC-350M-light with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "vasanth009/LC-350M-light"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "vasanth009/LC-350M-light" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use vasanth009/LC-350M-light with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "vasanth009/LC-350M-light"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "vasanth009/LC-350M-light"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "vasanth009/LC-350M-light",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

LC-350M-light / README.md

vasanth009

Upload folder using huggingface_hub

e1ba611 verified 1 day ago

preview code

Raw

History Blame Contribute Delete

1.42 kB

metadata

license: other
license_name: lfm-open-license
base_model: LiquidAI/LFM2.5-350M
tags:
  - mlx
  - dictation
  - speech-to-text
  - cleanup
  - polish
  - apple-silicon
  - lfm
  - lc-350m
language:
  - en
library_name: mlx
pipeline_tag: text-generation

LC-350M-light (Lint Clean)

Light on-device dictation transcript cleanup for Apple Silicon (MLX).

Fine-tuned from LiquidAI/LFM2.5-350M for MacWispr-style polish:

Remove stutters / exact word repeats
Light grammar, punctuation, capitalization
Keep meaning and almost all wording (no heavy rewrite)

For spoken self-corrections (“bag no not bag, my phone”), use LC-350M-smart instead.

Usage (MLX)

pip install mlx-lm
mlx_lm.generate --model vasanth009/LC-350M-light \
  --max-tokens 256 \
  --prompt "Clean this voice dictation lightly. Keep every idea.\n\nTranscript:\nsee we can improve the UI because currently it's it's glitching"

Training repo: github.com/vasanthsreeram/lc-350m
App: github.com/vasanthsreeram/macwispr
Smart variant: LC-350M-smart

License

Inherits Liquid LFM base model terms. Training code in the GitHub repo is Apache-2.0.

vasanth009
/

LC-350M-light

LC-350M-light (Lint Clean)

Usage (MLX)

Related

License