Instructions to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF: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 FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF: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 FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

Use Docker

docker model run hf.co/FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

Ollama
How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with Ollama:
```
ollama run hf.co/FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M
```

Unsloth Studio

How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF 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 FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF 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 FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF to start chatting

How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

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 "FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Docker Model Runner
How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M
```

Lemonade

How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-350M-heretic-imatrix-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

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 FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

FadedRedStar commited on 26 days ago

Commit

16edadc

verified ·

1 Parent(s): e4f30ab

Update README.md

Browse files

Files changed (1) hide show

README.md +149 -16

README.md CHANGED Viewed

@@ -2,35 +2,168 @@
 base_model: coder3101/LFM2.5-350M-heretic
 base_model_relation: quantized
 library_name: gguf
-license: apache-2.0
 language:
-- multilingual
 pipeline_tag: text-generation
 tags:
 - gguf
 - text-generation
-- reasoning
-- thinking
-- agentic
-- tool-use
-- abliterated
 - uncensored
-- lfm2
 - imatrix
 - conversational
 ---
-# LFM2.5-350M-heretic-imatrix — GGUF
 > [!NOTE]
-> This card is a work in progress. Full architecture details, abliteration parameters, and inference instructions will be added shortly.
-This repository hosts importance-matrix (imatrix) calibrated GGUF weights for **LFM2.5-350M-heretic**, quantized from the source floating-point tensors provided by [coder3101/LFM2.5-350M-heretic](https://huggingface.co/coder3101/LFM2.5-350M-heretic).
-## Repository Files
-| Filename | Format | Size | llama.cpp Build | Description |
 |---|---|---|---|---|
-| `LFM2.5-350M-heretic-IQ4_NL-imatrix.gguf` | IQ4_NL | 219 MB | b9860 | Main model weights, imatrix-calibrated, smaller non-linear 4-bit quant |
-| `LFM2.5-350M-heretic-Q4_K_M-imatrix.gguf` | Q4_K_M | 229 MB | b9860 | Main model weights, imatrix-calibrated |
-| `LFM2.5-350M-heretic-Q5_K_M-imatrix.gguf` | Q5_K_M | 260 MB | b9860 | Main model weights, imatrix-calibrated, higher fidelity |

 base_model: coder3101/LFM2.5-350M-heretic
 base_model_relation: quantized
 library_name: gguf
+license: other
+license_name: lfm-1.0
+license_link: https://huggingface.co/LiquidAI/LFM2.5-350M/blob/main/LICENSE
 language:
+- en
+- ar
+- zh
+- fr
+- de
+- ja
+- ko
+- es
+- pt
 pipeline_tag: text-generation
 tags:
 - gguf
+- llama.cpp
 - text-generation
+- heretic
+- liquid-ai
 - uncensored
 - imatrix
+- abliterated
 - conversational
+- iq4_nl
+- q4_k_m
+- q5_k_m
+quantized_by: FadedRedStar
 ---
+# 🤖 LFM2.5-350M-heretic — Importance Matrix GGUF
+This repository hosts importance-matrix (imatrix) optimized GGUF weights, available in multiple quantization formats, for **LFM2.5-350M-heretic**, quantized from the source floating-point tensors provided by [coder3101/LFM2.5-350M-heretic](https://huggingface.co/coder3101/LFM2.5-350M-heretic).
+**🔄 Sister Repository:** Check out the [Standard GGUF Sister Repository](https://huggingface.co/FadedRedStar/LFM2.5-350M-heretic-GGUF) for uncalibrated and full 8-bit precision options.
+## 🎯 Matrix-Weighted Calibration (Imatrix)
+An **Importance Matrix (imatrix)** calculation tracks activations across network layers using a calibration sequence, then weights the quantization process to preserve the parameters that matter most for output quality — improving fidelity at low bit depths.
+➡️ **Calibration dataset:** Bartowski's `calibration_datav5.txt`.
+> [!NOTE]
+> * **`IQ4_NL` is included** because the matrix enables a non-linear 4-bit format that outperforms standard linear 4-bit quantization.
+> * **`Q8_0` is absent** because 8-bit quantization already introduces near-zero degradation, making calibration unnecessary — see the standard sister repository for that variant.
+## ℹ️ Model Profile & Core Features
+**LFM2.5-350M** is the smallest text-only model in Liquid AI's **Liquid Foundation Model 2.5** series, built for extreme on-device and edge deployment. It shares the family's hybrid architecture of double-gated LIV (Liquid, Input-adaptive, Value-selective) convolution layers interleaved with GQA (Grouped Query Attention) layers, pre-trained on 28 trillion tokens with large-scale reinforcement learning post-training. Despite its size, it is tuned for **instruction following, lightweight tool calling, and structured data extraction**, with day-one support across llama.cpp, MLX, vLLM, SGLang, ONNX, and OpenVINO.
+The **heretic** suffix denotes post-processing via the **[Heretic v1.3.0](https://github.com/p-e-w/heretic)** method performed by [coder3101](https://huggingface.co/coder3101), which removes refusal conditioning while preserving the model's lightweight instruction-following behavior.
+## 📋 Technical Specifications
+| Property | Value |
+|---|---|
+| **Base Architecture** | LFM2 hybrid (double-gated LIV conv + GQA) |
+| **Developed by** | Liquid AI |
+| **Total Parameters** | 350M |
+| **Primary Use** | Instruction following, lightweight tool calling, structured extraction |
+| **Context Window** | 131,072 tokens |
+| **Training Budget** | 28 trillion tokens |
+| **Languages** | English, Arabic, Chinese, French, German, Japanese, Korean, Spanish, Portuguese |
+| **Abliteration Tool** | Heretic v1.3.0 |
+| **Prompt Format** | ChatML |
+## 🛠️ Heretic Overrides (ARA)
+| Property | Value |
+|---|---|
+| **direction_index** | per layer |
+| **attn.o_proj.max_weight** | 1.08 |
+| **attn.o_proj.max_weight_position** | 10.46 |
+| **attn.o_proj.min_weight** | 0.87 |
+| **attn.o_proj.min_weight_distance** | 3.56 |
+| **mlp.down_proj.max_weight** | 1.44 |
+| **mlp.down_proj.max_weight_position** | 12.00 |
+| **mlp.down_proj.min_weight** | 1.22 |
+| **mlp.down_proj.min_weight_distance** | 1.97 |
+## 📊 Refusal Bypass Metrics
 > [!NOTE]
+> The metrics below are self-reported by the original model author ([coder3101](https://huggingface.co/coder3101)) and have not been independently reproduced.
+| Metric | This model | Original ([LiquidAI/LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M)) |
+|---|---|---|
+| **KL divergence** | 0.0440 | 0 *(by definition)* |
+| **Refusals** | 6/100 | 90/100 |
+## 🧮 Numerical & Tensor Formats
+| Property | Value |
+|---|---|
+| **Quantization Types** | IQ4_NL, Q4_K_M, Q5_K_M (all with imatrix calibration) |
+| **Importance Matrix** | Bartowski's `calibration_datav5.txt` |
+## 📦 Available Model Files
+**Main model weights**
+| Filename | Quantization | llama.cpp Build | Size | Download |
 |---|---|---|---|---|
+| `LFM2.5-350M-heretic-IQ4_NL-imatrix.gguf` | `IQ4_NL` | `b9860` | 209 MB | [📥 Download](https://huggingface.co/FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF/resolve/main/LFM2.5-350M-heretic-IQ4_NL-imatrix.gguf) |
+| `LFM2.5-350M-heretic-Q4_K_M-imatrix.gguf` | `Q4_K_M` | `b9860` | 219 MB | [📥 Download](https://huggingface.co/FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF/resolve/main/LFM2.5-350M-heretic-Q4_K_M-imatrix.gguf) |
+| `LFM2.5-350M-heretic-Q5_K_M-imatrix.gguf` | `Q5_K_M` | `b9860` | 248 MB | [📥 Download](https://huggingface.co/FadedRedStar/LFM2.5-350M-heretic-imatrix-GGUF/resolve/main/LFM2.5-350M-heretic-Q5_K_M-imatrix.gguf) |
+## 🎛️ Component Pairing Guide
+Download exactly **one** main weights file:
+* **`IQ4_NL`**: Non-linear 4-bit format, best choice for constrained memory when imatrix calibration is present.
+* **`Q4_K_M`**: Balanced 4-bit format suitable for most everyday use.
+* **`Q5_K_M`**: Higher-fidelity mid-range format recommended as a general default.
+## ⚡ Deployment & Execution Commands
+> [!NOTE]
+> Liquid AI recommends the following generation parameters for best results: `temperature: 0.1`, `top_k: 50`, `repetition_penalty: 1.05`.
+> [!TIP]
+> Swap the `-m` filename below for either quantized file depending on your size/quality trade-off preference.
+### llama.cpp CLI
+```bash
+./llama-cli \
+  -m LFM2.5-350M-heretic-IQ4_NL-imatrix.gguf \
+  -c 8192 \
+  -ngl 99 \
+  --temp 0.3 \
+  --top-k 40 \
+  --repeat-penalty 1.05 \
+  -p "<|im_start|>system\nYou are a concise, helpful assistant.<|im_end|>\n<|im_start|>user\nState the capital of Italy and one interesting fact about it.<|im_end|>\n<|im_start|>assistant\n"
+```
+### OpenAI-Compatible API Server
+```bash
+./llama-server \
+  --host 0.0.0.0 \
+  --port 8080 \
+  -m LFM2.5-350M-heretic-IQ4_NL-imatrix.gguf \
+  -c 16384 \
+  -ngl 99 \
+  --flash-attn
+```
+## 💬 Chat Templates & Prompt Design (ChatML)
+```text
+<|im_start|>system
+You are a capable assistant. Follow instructions precisely.<|im_end|>
+<|im_start|>user
+Your task or query here.<|im_end|>
+<|im_start|>assistant
+```
+## ⚠️ Safety & Operational Notes
+- This model is abliterated and will generate content that standard aligned models refuse. Use responsibly and in compliance with applicable laws.
+- This is a **text-only** model — it has no vision encoder and cannot process images.
+- Despite its small footprint, IFBench and structured-extraction benchmarks show substantial generational gains over LFM2 predecessors.
+- Best suited for constrained hardware: CPUs, NPUs, and edge devices rather than complex reasoning workloads.
+- Imatrix calibration improves perplexity recovery compared to non-imatrix quantization, particularly on low-frequency tokens.
+- IQ4_NL produces a smaller file than Q4_K_M and tends to run faster on CPU and ARM devices; imatrix calibration narrows the quality gap between the two formats considerably.