metadata
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
Quickstart
- Ensure that you have release
b2636
or newer. - Start with the command below:
./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]
Test | PPL Value | Standard Deviation |
---|---|---|
Q2_K | 5.7178 | +/- 0.03418 |
Q3_K_L | 4.6214 | +/- 0.02629 |
Q4_K_M | 4.4625 | +/- 0.02522 |
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:
./gguf-split --merge /path/to/command-r-plus-f16-00001-of-00005.gguf /path/to/command-r-plus-f16-combined.gguf