README.md

---
inference: false
license: other
---

# Tim Dettmers' Guanaco 65B GGML

These files are GGML format model files for [Tim Dettmers' Guanaco 65B](https://huggingface.co/timdettmers/guanaco-65b).

GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)

## Other repositories available

* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/guanaco-65B-GPTQ)
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/guanaco-65B-GGML)
* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/guanaco-65B-HF)

## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!

llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508

I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit `2d5db48` or later) to use them.

## Provided files
| Name | Quant method | Bits | Size | RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| guanaco-65B.ggmlv3.q4_0.bin | q4_0 | 4 | 36.73 GB | 39.23 GB | 4-bit. |
| guanaco-65B.ggmlv3.q4_1.bin | q4_1 | 4 | 40.81 GB | 43.31 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| guanaco-65B.ggmlv3.q5_0.bin | q5_0 | 5 | 44.89 GB | 47.39 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
| guanaco-65B.ggmlv3.q5_1.bin | q5_1 | 5 | 48.97 GB | 51.47 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
| guanaco-65B.ggmlv3.q8_0.bin | q8_0 | 8 | 69.370 GB | 71.87 GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for most use cases. |

### q8_0 file requires expansion from archive

**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the q8_0 file in a multi-part ZIP file. The ZIP is not compressed, it is just storing the .bin file in two parts.

To decompress it, please download
* `guanaco-65B.ggmlv3.q8_0.zip`
* `guanaco-65B.ggmlv3.q8_0.z01`

and extract the .zip archive. This will will expand both parts automatically. On Linux I found I had to use `7zip` - the basic `unzip` tool did not work. Example:
```
sudo apt update -y && sudo apt install 7zip
7zz x guanaco-65B.ggmlv3.q8_0.zip # Once the q8_0.bin is extracted you can delete the .zip and .z01
```

On Windows you can hopefully just double-click the ZIP and extract it. If that fails, download WinRAR.

## How to run in `llama.cpp`

I use the following command line; adjust for your tastes and needs:

```
./main -t 12 -m guanaco-65B.v3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Write a story about llamas
### Response:"
```
Change `-t 12` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.

If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`

## How to run in `text-generation-webui`

Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).

Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.

# Original model card: Tim Dettmers' Guanaco 65B