Instructions to use mindi-dev/experience-extractor-1.2b-v1-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mindi-dev/experience-extractor-1.2b-v1-mlx-8bit 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("mindi-dev/experience-extractor-1.2b-v1-mlx-8bit")

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 mindi-dev/experience-extractor-1.2b-v1-mlx-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit"

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": "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mindi-dev/experience-extractor-1.2b-v1-mlx-8bit 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 "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit"

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 mindi-dev/experience-extractor-1.2b-v1-mlx-8bit

Run Hermes

hermes

OpenClaw new

How to use mindi-dev/experience-extractor-1.2b-v1-mlx-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit"

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 "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit" \
  --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 mindi-dev/experience-extractor-1.2b-v1-mlx-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mindi-dev/experience-extractor-1.2b-v1-mlx-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

experience-extractor-1.2b-v1-mlx-8bit / NOTICE.md

mindi-dev

Upload folder using huggingface_hub

fe69648 verified 21 days ago

preview code

Raw

History Blame Contribute Delete

1.29 kB

NOTICE — license & attribution

This model is a fine-tune of LiquidAI/LFM2-1.2B-Extract and is therefore governed by the LFM Open License v1.0 (the LiquidAI lfm1.0 license), NOT the MIT license of the experience source code.

Change notice (Sec. 4): fine-tuned from LiquidAI/LFM2-1.2B-Extract by the experience/mindi-dev project into a structured fact extractor, by LoRA (rank 32) fine-tune (mlx-lm) on real-distribution chat transcripts with teacher-generated labels. Architecture unchanged (lfm2).

Commercial-use gate (Sec. 5), inherited by you: Commercial Use by an entity with ≥ US$10M annual revenue is NOT licensed without a Liquid AI commercial license. Below that, use is permitted under the LFM Open License v1.0.

You must include the full LFM Open License v1.0 in this repo — fetch it from the base model:

hf download LiquidAI/LFM2-1.2B-Extract LICENSE --local-dir .   # or copy LICENSE/LICENSE.md from LiquidAI/LFM2-1.2B-Extract

Training labels were teacher-generated (Claude / GPT-5.5-via-codex). Only weights are distributed here, not the dataset.