Update README.md

README.md

@@ -17,6 +17,32 @@ tags:
 
 This repo contains the [IIC/RigoChat-7b-v2](https://huggingface.co/IIC/RigoChat-7b-v2) model in the GGUF Format, with the original weights and quantized to different precisions.
 
+The [llama.cpp](https://github.com/ggerganov/llama.cpp) library has been used to transform the parameters into GGUF format, as well as to perform the quantizations. Specifically, the following command has been used to obtain the model in full precision:
+
+1. To download the weights:
+
+```python
+from huggingface_hub import snapshot_download
+import os
+
+model_id="IIC/RigoChat-7b-v2"
+
+os.environ["MODEL_DIR"] = snapshot_download(
+    repo_id=model_id,
+    local_dir="model",
+    local_dir_use_symlinks=False,
+    revision="main",
+)
+```
+
+2. To transform to `FP16`:
+
+```shell
+python ../llama.cpp/convert_hf_to_gguf.py $MODEL_DIR --outfile rigochat-7b-v2-F16.gguf --outtype f16
+```
+
+Yo can download this weights [here](https://huggingface.co/IIC/RigoChat-7b-v2-GGUF/blob/main/rigochat-7b-v2-F16.gguf).
+
 ## How to Get Started with the Model 
 
 ## Evaluation