Update README.md

README.md

@@ -65,10 +65,9 @@ It uses SFT to move the base model away from generic AI prose and toward specifi
 ### v2 — Style + Behavioral Fine-Tuning
 
 - Adds DPO training, larger amounts of synthetic data, and on-policy sampling on top of the v1 recipe.
-
 - Output is more precise, more stable, and shows fewer habitual "AI-shaped" patterns.
-
-- Available in multiple formats: HF PEFT safetensors / GGUF LoRA / MLX LoRA.
+- Available formats: HF PEFT safetensors and GGUF LoRA.
+- MLX users may also be able to use the PEFT safetensors through mlx-lm depending on their local setup.
 
 v2 models are documented in their own repositories.
 
@@ -77,10 +76,10 @@ v2 models are documented in their own repositories.
 ## 🌱 Status
 
 | Field | Value |
-|-------|-------|
+|---|---|
 | Version | v2 |
 | Focus | Chinese suspense / crime-fiction behavior |
-| Format | HF PEFT LoRA adapter |
+| Format | HF PEFT safetensors + GGUF LoRA |
 | Base model | Qwen3.6-27B |
 | Language | Chinese |
 | Use case | fiction drafting, scene rewriting, POV-controlled suspense prose |
@@ -114,11 +113,12 @@ They are intentionally split: the pipeline owns *what happens*, the LoRA owns *h
 
 ## 📦 Files
 
-This repository provides the LoRA adapter in HF PEFT format:
+This repository provides the LoRA adapter in both HF PEFT and GGUF LoRA formats:
 
 ```text
 adapter_config.json
 adapter_model.safetensors
+qwen3-6-27b-chinese-crime-fiction-lora-v2-f16.gguf
 tokenizer.json
 tokenizer_config.json
 chat_template.jinja
@@ -127,6 +127,8 @@ README.md
 
 This is not a full model.
 
+The GGUF file is a LoRA adapter for llama.cpp-style inference. It is not a merged full model.
+
 To use it, load the Qwen3.6-27B base model and then apply this adapter.
 
 ---
@@ -183,10 +185,35 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ---
 
+## 🚀 Example llama.cpp Usage
+
+Use a compatible Qwen3.6-27B GGUF base model, then load this GGUF LoRA adapter with `--lora`:
+
+```bash
+llama-server \
+  -m path/to/qwen3.6-27b-base.gguf \
+  --lora qwen3-6-27b-chinese-crime-fiction-lora-v2-f16.gguf \
+  --ctx-size 16384 \
+  --n-gpu-layers 99 \
+  --port 18084
+```
+
+For Windows PowerShell:
+
+```powershell
+C:\llama.cpp\llama-server.exe `
+  -m "C:\path\to\qwen3.6-27b-base.gguf" `
+  --lora "C:\path\to\qwen3-6-27b-chinese-crime-fiction-lora-v2-f16.gguf" `
+  --ctx-size 16384 `
+  --n-gpu-layers 99 `
+  --port 18084
+```
+
+---
+
 ## 🧪 Example Prompts
 
-This adapter was trained on a mixture of detailed prompts, short prompts, and minimal one-line instructions.
-It does not require a long system prompt to start writing fiction prose.
+This adapter was trained on a mixture of detailed prompts, short prompts, and minimal one-line instructions. It does not require a long system prompt to start writing fiction prose.
 
 Example prompts:
 
@@ -221,7 +248,7 @@ A small 30-prompt internal evaluation was used to track behavioral progress duri
 Behavioral progression (SFT → final v2):
 
 | Metric | SFT baseline | Final v2 |
-|--------|--------------|----------|
+|---|---:|---:|
 | Exposition-pattern hits | 6 | 3 (−50%) |
 | Clean prose outputs | 28 / 30 | 28 / 30 |
 | Meta / explanation leakage | 2 / 30 | 2 / 30 |