|
--- |
|
base_model: CohereForAI/c4ai-command-r-plus |
|
language: |
|
- en |
|
- fr |
|
- de |
|
- es |
|
- it |
|
- pt |
|
- ja |
|
- ko |
|
- zh |
|
- ar |
|
library_name: transformers |
|
license: cc-by-nc-4.0 |
|
quantized_by: mradermacher |
|
--- |
|
## About |
|
|
|
<!-- ### quantize_version: 1 --> |
|
<!-- ### output_tensor_quantised: 1 --> |
|
<!-- ### convert_type: --> |
|
<!-- ### vocab_type: --> |
|
static quants of https://huggingface.co/CohereForAI/c4ai-command-r-plus |
|
|
|
**You should use `--override-kv tokenizer.ggml.pre=str:command-r` and a current llama.cpp version to work around a bug in llama.cpp that made these quants.** |
|
|
|
<!-- provided-files --> |
|
weighted/imatrix quants are available at https://huggingface.co/mradermacher/c4ai-command-r-plus-i1-GGUF |
|
## Usage |
|
|
|
If you are unsure how to use GGUF files, refer to one of [TheBloke's |
|
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for |
|
more details, including on how to concatenate multi-part files. |
|
|
|
## Provided Quants |
|
|
|
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) |
|
|
|
| Link | Type | Size/GB | Notes | |
|
|:-----|:-----|--------:|:------| |
|
| [GGUF](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q2_K.gguf) | Q2_K | 39.6 | | |
|
| [GGUF](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.IQ3_XS.gguf) | IQ3_XS | 43.7 | | |
|
| [GGUF](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q3_K_S.gguf) | Q3_K_S | 46.0 | | |
|
| [GGUF](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.IQ3_S.gguf) | IQ3_S | 46.1 | beats Q3_K* | |
|
| [GGUF](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.IQ3_M.gguf) | IQ3_M | 47.8 | | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q3_K_M.gguf.part2of2) | Q3_K_M | 51.1 | lower quality | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q3_K_L.gguf.part2of2) | Q3_K_L | 55.5 | | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.IQ4_XS.gguf.part2of2) | IQ4_XS | 56.8 | | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q4_K_S.gguf.part2of2) | Q4_K_S | 59.7 | fast, recommended | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q4_K_M.gguf.part2of2) | Q4_K_M | 62.9 | fast, recommended | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q5_K_S.gguf.part2of2) | Q5_K_S | 71.9 | | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q5_K_M.gguf.part2of2) | Q5_K_M | 73.7 | | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q6_K.gguf.part2of2) | Q6_K | 85.3 | very good quality | |
|
| [PART 1](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/c4ai-command-r-plus-GGUF/resolve/main/c4ai-command-r-plus.Q8_0.gguf.part3of3) | Q8_0 | 110.4 | fast, best quality | |
|
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant |
|
types (lower is better): |
|
|
|
 |
|
|
|
And here are Artefact2's thoughts on the matter: |
|
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 |
|
|
|
## FAQ / Model Request |
|
|
|
See https://huggingface.co/mradermacher/model_requests for some answers to |
|
questions you might have and/or if you want some other model quantized. |
|
|
|
## Thanks |
|
|
|
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting |
|
me use its servers and providing upgrades to my workstation to enable |
|
this work in my free time. |
|
|
|
<!-- end --> |
|
|
