Update README.md

README.md

@@ -2,46 +2,51 @@
 base_model: coder3101/LFM2.5-8B-A1B-heretic
 base_model_relation: quantized
 library_name: gguf
-license: apache-2.0
+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
-- it
 - ja
 - ko
-- pt
 - es
+- pt
 pipeline_tag: text-generation
 tags:
 - gguf
+- llama.cpp
 - text-generation
-- reasoning
-- instruction-following
-- agentic
-- tool-use
-- abliterated
+- heretic
+- liquid-ai
 - uncensored
-- lfm2
-- q4_k_m
+- abliterated
 - conversational
+- q4_k_m
+- q5_k_m
+- q8_0
+quantized_by: FadedRedStar
 ---
 
-# LFM2.5-8B-A1B-heretic — GGUF
+# 🤖 LFM2.5-8B-A1B-heretic — GGUF
 
 This repository hosts GGUF weights for **LFM2.5-8B-A1B-heretic**, quantized from the source floating-point tensors provided by [coder3101/LFM2.5-8B-A1B-heretic](https://huggingface.co/coder3101/LFM2.5-8B-A1B-heretic).
 
-## About the Model
+**🔄 Sister Repository:** Check out the [Imatrix Sister Repository](https://huggingface.co/FadedRedStar/LFM2.5-8B-A1B-heretic-imatrix-GGUF) for enhanced precision at lower bit fractions.
+
+> [!NOTE]
+> If you plan on using 4-bit or 5-bit variants, consider the **imatrix** sister repository instead — importance matrix calibration improves logic retention at those bit depths. This repository is best suited if you want the near-lossless `Q8_0` build.
+
+## ℹ️ Model Profile & Core Features
 
 **LFM2.5-8B-A1B** is a text-only model from Liquid AI's **Liquid Foundation Model 2.5** series, designed for on-device deployment. It uses a hybrid architecture with **24 layers — 18 double-gated LIV (Liquid, Input-adaptive, Value-selective) convolution layers plus 6 GQA (Grouped Query Attention) layers** — activating only approximately **1.5B parameters per forward pass** out of 8.3B total. This delivers fastest-in-class throughput at its size on both CPU and GPU, with day-one support for llama.cpp, MLX, vLLM, and SGLang. The model is a **reasoning model**: it produces a chain-of-thought before its final answer, and is tuned for **complex instruction following, tool calling, and chained agentic task execution**.
 
 The **heretic** suffix denotes post-processing via the **[Heretic v1.2.0 Arbitrary-Rank Ablation (ARA)](https://github.com/p-e-w/heretic)** method with row-norm preservation performed by [coder3101](https://huggingface.co/coder3101), which removes refusal conditioning at multiple tensor ranks while maintaining the model's instruction-following and planning capabilities.
 
----
-
-## Model & Architecture Specifications
+## 📋 Technical Specifications
 
 | Property | Value |
 |---|---|
@@ -52,16 +57,14 @@ The **heretic** suffix denotes post-processing via the **[Heretic v1.2.0 Arbitra
 | **Primary Use** | Reasoning, instruction following, tool calling, agentic tasks |
 | **Context Window** | 128,000 tokens |
 | **Training Budget** | 38 trillion tokens |
-| **Languages** | English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish |
+| **Languages** | English, Arabic, Chinese, French, German, Japanese, Korean, Spanish, Portuguese |
 | **Abliteration Tool** | Heretic v1.2.0 |
 | **Abliteration Method** | Arbitrary-Rank Ablation (ARA) with row-norm preservation |
 | **Prompt Format** | ChatML |
 
----
-
-## Abliteration Parameters
+## 🛠️ Heretic Overrides (ARA)
 
-| Parameter | Value |
+| Property | Value |
 |---|---|
 | **start_layer_index** | 7 |
 | **end_layer_index** | 21 |
@@ -70,7 +73,7 @@ The **heretic** suffix denotes post-processing via the **[Heretic v1.2.0 Arbitra
 | **overcorrect_relative_weight** | 0.9494 |
 | **neighbor_count** | 8 |
 
-## Abliteration Performance
+## 📊 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.
@@ -80,32 +83,30 @@ The **heretic** suffix denotes post-processing via the **[Heretic v1.2.0 Arbitra
 | **KL divergence** | 0.0239 | 0 *(by definition)* |
 | **Refusals** | 12/100 | 91/100 |
 
----
-
-## Quantization Details
+## 🧮 Numerical & Tensor Formats
 
 | Property | Value |
 |---|---|
-| **Quantization Type** | Q4_K_M |
+| **Quantization Type** | Q4_K_M, Q5_K_M, Q8_0 |
 
-### Quantization Command
+## 📦 Available Model Files
 
-```bash
-./llama-quantize /content/model-bf16.gguf \
-  /content/LFM2.5-8B-A1B-heretic-Q4_K_M.gguf q4_k_m
-```
-
----
+**Main model weights**
+| Filename | Quantization | llama.cpp Build | Size | Download |
+|---|---|---|---|---|
+| `LFM2.5-8B-A1B-heretic-Q4_K_M.gguf` | `Q4_K_M` | `b9803` | 4.80 GB | [📥 Download](https://huggingface.co/FadedRedStar/LFM2.5-8B-A1B-heretic-GGUF/resolve/main/LFM2.5-8B-A1B-heretic-Q4_K_M.gguf) |
+| `LFM2.5-8B-A1B-heretic-Q5_K_M.gguf` | `Q5_K_M` | `b9870` | 5.62 GB | [📥 Download](https://huggingface.co/FadedRedStar/LFM2.5-8B-A1B-heretic-GGUF/resolve/main/LFM2.5-8B-A1B-heretic-Q5_K_M.gguf) |
+| `LFM2.5-8B-A1B-heretic-Q8_0.gguf` | `Q8_0` | `b9870` | 8.39 GB | [📥 Download](https://huggingface.co/FadedRedStar/LFM2.5-8B-A1B-heretic-GGUF/resolve/main/LFM2.5-8B-A1B-heretic-Q8_0.gguf) |
 
-## Repository Files
+## 🎛️ Component Pairing Guide
 
-| Filename | Format | Size | llama.cpp Build | Description |
-|---|---|---|---|---|
-| `LFM2.5-8B-A1B-heretic-Q4_K_M.gguf` | Q4_K_M | 5.16 GB | b9803 | Main model weights |
+Download exactly **one** main weights file:
 
----
+* **`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.
+* **`Q8_0`**: Near-lossless 8-bit format for when memory is not a constraint.
 
-## Inference
+## ⚡ Deployment & Execution Commands
 
 > [!NOTE]
 > Liquid AI recommends the following generation parameters for best results: `temperature: 0.2`, `top_k: 80`, `repetition_penalty: 1.05`.
@@ -113,6 +114,9 @@ The **heretic** suffix denotes post-processing via the **[Heretic v1.2.0 Arbitra
 > [!NOTE]
 > This model emits reasoning content before its final answer. If you require a clean final answer only, parse the output accordingly rather than expecting a single direct response.
 
+> [!TIP]
+> Swap the `-m` filename below for either quantized file depending on your size/quality trade-off preference.
+
 ### llama.cpp CLI
 
 ```bash
@@ -138,9 +142,7 @@ The **heretic** suffix denotes post-processing via the **[Heretic v1.2.0 Arbitra
   --flash-attn
 ```
 
----
-
-## Prompt Format (ChatML)
+## 💬 Chat Templates & Prompt Design (ChatML)
 
 ```text
 <|im_start|>system
@@ -150,9 +152,7 @@ Your task or query here.<|im_end|>
 <|im_start|>assistant
 ```
 
----
-
-## Notes & Limitations
+## ⚠️ 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.