Update README.md

README.md

@@ -1,14 +1,29 @@
 ---
 license: cc-by-nc-4.0
+pipeline_tag: text-generation
+base_model: CohereForAI/c4ai-command-r-plus
 ---
 
 # Command R+ GGUF
 
 ## Description
-This repository contains GGUF weights for the `llama.cpp`
+This repository contains experimental GGUF weights that are currently compatible with [pull request #6491](https://github.com/ggerganov/llama.cpp/pull/6491) in the `llama.cpp`. I will update them once support for Command R+ is merged into the llama.cpp repository.
 
-## Concatenating Weights
-For every variant (except Q2_K), you must concatenate the weights, as they exceed the 50 GB single file size limit on HuggingFace. You can accomplish this using the `cat` command on Linux (example for the Q3 variant):
+## Getting started
+1. Clone the `Carolinabanana/llama.cpp` repository:
 ```bash
-cat command-r-plus-Q3_K_L-0000* > command-r-plus-Q3_K_L.gguf
+git clone https://github.com/Carolinabanana/llama.cpp.git llama.cpp-fork
+cd llama.cpp-fork
+git reset --hard 8b6577bd631fec33eeadb4b9dfc5a07ed2118148
+```
+2. Build it using `make`
+3. Use it in the same way as the regular `llama.cpp`. If you're unsure of how to start, you can use the following command as a starting point:
+```bash
+./main -p "<|START_OF_TURN_TOKEN|><|USER_TOKEN|>Who are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>" --color -m /path/to/command-r-plus-Q3_K_L-00001-of-00002.gguf
+```
+
+## Merging Weights
+After commit `8a28d12`, weights are split with `gguf-split`, which means that you don't have to merge weights. Simply pass the first split, as in the example above, and `llama.cpp` will automatically load all splits. If, for some reason, you want to merge splits, you can use the following command:
+```bash
+./gguf-split --merge /path/to/command-r-plus-f16-00001-of-00005.gguf /path/to/command-r-plus-f16-combined.gguf
 ```