Update README.md

Updated description

README.md

@@ -3,39 +3,34 @@ license: apache-2.0
 base_model: syntheticlab/fix-json
 tags:
 - llama-cpp
-- gguf-my-repo
+- gguf
+- lora
+- merged-model
 ---
 
-# fix-json
+# fix-json (LoRA Merged GGUF)
 
-**Model creator:** [syntheticlab](https://huggingface.co/syntheticlab)<br/>
-**Original model**: [syntheticlab/fix-json](https://huggingface.co/syntheticlab/fix-json)<br/>
-**GGUF quantization:** provided by [CronoBJS](https:/huggingface.co/CronoBJS) using `llama.cpp`<br/>
+**Model creator:** [syntheticlab](https://huggingface.co/syntheticlab)  
+**Base model required:** [syntheticlab/fix-json](https://huggingface.co/syntheticlab/fix-json) (Meta-Llama-3.1-8B-Instruct)  
+**GGUF conversion & quantization:** by [CronoBJS](https://huggingface.co/CronoBJS) using [`llama.cpp`](https://github.com/ggerganov/llama.cpp)  
 
-## Special thanks
-
-🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
-
-## Use with Ollama
-
-```bash
-ollama run "hf.co/CronoBJS/fix-json-GGUF:<quantization>"
-```
+⚠️ **Important:**  
+This file is a **merged LoRA adapter in GGUF format**. It is **not** a standalone model.  
+You **must** also have the original base GGUF model (e.g., `Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf`) to run it.  
+Use the `--lora` or `--lora-scaled` flags in `llama.cpp` to apply it at runtime.
 
-## Use with LM Studio
+---
 
-```bash
-lms load "CronoBJS/fix-json-GGUF"
-```
+## Special thanks
 
-## Use with llama.cpp CLI
+🙏 Thanks to [Georgi Gerganov](https://github.com/ggerganov) and the [llama.cpp team](https://github.com/ggerganov/llama.cpp) for making all of this possible.
 
-```bash
-llama-cli --hf-repo "CronoBJS/fix-json-GGUF" --hf-file "fix-json-Q8_0.gguf" -p "The meaning to life and the universe is"
-```
+---
 
-## Use with llama.cpp Server:
+## Running the Model
 
+### 1️⃣ llama.cpp CLI
 ```bash
-llama-server --hf-repo "CronoBJS/fix-json-GGUF" --hf-file "fix-json-Q8_0.gguf" -c 4096
-```
+llama-cli -m "path/to/Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf" \
+  --lora "path/to/syntheticlab-fix-json-lora.gguf" \
+  -c 2048 -n 256 -p "Your prompt here"