Instructions to use vasanth009/LC-lfm2.5-350m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vasanth009/LC-lfm2.5-350m 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-lfm2.5-350m")

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-lfm2.5-350m 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-lfm2.5-350m"

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-lfm2.5-350m"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vasanth009/LC-lfm2.5-350m 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-lfm2.5-350m"

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-lfm2.5-350m

Run Hermes

hermes

OpenClaw new

How to use vasanth009/LC-lfm2.5-350m 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-lfm2.5-350m"

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-lfm2.5-350m" \
  --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-lfm2.5-350m 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-lfm2.5-350m"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "vasanth009/LC-lfm2.5-350m"
# 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-lfm2.5-350m",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

LC-lfm2.5-350m / README.md

vasanth009

Fused LFM2.5-350M dictation cleanup + course-correction LoRA

76b33c3 verified 1 day ago

3.52 kB

license: other
license_name: lfm-open
base_model: juanquivilla/sotto-cleanup-lfm25-350m-mlx-5bit
library_name: mlx
tags:
  - mlx
  - lfm2
  - text-cleanup
  - dictation
  - course-correction
  - lora
language:
  - en
pipeline_tag: text-generation

LC-lfm2.5-350m — dictation cleanup with course-correction

A small, fast on-device voice-dictation cleanup model: it turns messy spoken transcripts into clean written text, and — unlike most cleanup models — it honors spoken self-corrections ("book the 7pm flight no wait the 9pm one" → "Book the 9pm flight.").

Built for MacWispr. This repo ships the fused model (LoRA baked in) so you can pull and run it directly; the standalone LoRA adapter is under lora-adapter/.

Base: juanquivilla/sotto-cleanup-lfm25-350m-mlx-5bit (LFM2.5-350M, MLX 5-bit)
Method: LoRA (8 layers, 600 iters, LR 5e-6), fused into the base
Runtime: MLX (Apple Silicon) — also loadable in Swift via mlx-swift-lm (LFM2)

What it does

Removes fillers and stutters ("um", "uh", "that that" → "that").
Honors self-corrections — drops the retracted item, keeps the replacement, and keeps the rest of the sentence.
Writes numbers as digits ("three seventy-five" → "375").
Fixes light grammar/punctuation/capitalization without summarizing.

Prompt format

Trained on a raw completion format (not a chat template):

### Input:
{raw dictation}

### Output:

Usage (mlx-lm)

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tok = load("vasanth009/LC-lfm2.5-350m")
raw = "set the oven to three fifty no wait three seventy five for the lasagna"
prompt = f"### Input:\n{raw}\n\n### Output:\n"
out = generate(model, tok, prompt=prompt, max_tokens=64, sampler=make_sampler(temp=0.0))
print(out.split("###")[0].strip())
# -> Set the oven to 375 for the lasagna.

To apply the LoRA to the base yourself instead of using the fused weights:

mlx_lm.generate --model juanquivilla/sotto-cleanup-lfm25-350m-mlx-5bit \
  --adapter-path lora-adapter --prompt "### Input:\n...\n\n### Output:\n"

Honest evaluation (leak-free held-out)

Graded by an LLM judge on a 94-item held-out set generated on topics disjoint from training (0/94 overlap with the training data — verified). This is a real generalization test, not memorized phrases.

Model	Course-correction	Light cleanup	Preserve (anti over-edit)
Base (Sotto LFM2.5-350M)	10/16	12/12	6/8
This model (+LoRA)	13/16	12/12	7/8

Course-correction is the headline improvement (10→13/16). Light cleanup was already strong (tie). Latency ~50–100 ms/utterance on Apple Silicon.

Limitations

The base is 5-bit quantized; rare token corruptions can occur ("simmer" → "smear"). A higher-precision base would reduce this.
350M parameters — capable for cleanup, not a general assistant. It only cleans text; it does not answer questions in the transcript.
Occasionally over-shortens a long correction (drops a trailing clause).

Provenance

Training data (course-correction / light-cleanup / preserve pairs) was generated and QC-filtered with an LLM on fresh topics, with a hard leakage gate against the held-out eval. See the MacWispr repo's bench/polish_finetune/ for the full, reproducible pipeline.