|
--- |
|
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 `llama.cpp`. Support for them was added in release [`b2636`](https://github.com/ggerganov/llama.cpp/releases/tag/b2636). Since commit `dd2d53a`, all weights in this repo have chat templates. |
|
|
|
In the folder `imatrix`, you can find imatrix quants. The importance matrix was trained using [kalomaze's](https://github.com/kalomaze) [`groups_merged.txt`](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384). |
|
|
|
|
|
## Quickstart |
|
1. Ensure that you have release [`b2636`](https://github.com/ggerganov/llama.cpp/releases/tag/b2636) or newer. |
|
2. Start with the command below: |
|
```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 |
|
``` |
|
|
|
## Perplexity on `wikitext-2-raw` [WIP] |
|
| Variant | PPL Value | Standard Deviation | |
|
|----------|-----------|--------------------| |
|
| Q2_K | 5.7178 | +/- 0.03418 | |
|
| Q3_K_L | 4.6214 | +/- 0.02629 | |
|
| Q4_K_M | 4.4625 | +/- 0.02522 | |
|
| f16 | 4.3845 | +/- 0.02468 | |
|
|
|
## 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 |
|
``` |
|
|
