Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ This repo is the result of quantising to 4bit and 5bit GGML for CPU inference us
|
|
| 21 |
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GGML).
|
| 22 |
* [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF).
|
| 23 |
|
| 24 |
-
## REQUIRES LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!
|
| 25 |
|
| 26 |
llama.cpp recently made a breaking change to its quantisation methods.
|
| 27 |
|
|
@@ -29,6 +29,8 @@ I have quantised the GGML files in this repo with the latest version. Therefore
|
|
| 29 |
|
| 30 |
If you are currently unable to update llama.cpp, eg because you use a UI which hasn't updated yet, you can find GGMLs compatible with the older llama.cpp code in branch `previous_llama`
|
| 31 |
|
|
|
|
|
|
|
| 32 |
## Provided files
|
| 33 |
| Name | Quant method | Bits | Size | RAM required | Use case |
|
| 34 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
|
|
|
| 21 |
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GGML).
|
| 22 |
* [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF).
|
| 23 |
|
| 24 |
+
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!
|
| 25 |
|
| 26 |
llama.cpp recently made a breaking change to its quantisation methods.
|
| 27 |
|
|
|
|
| 29 |
|
| 30 |
If you are currently unable to update llama.cpp, eg because you use a UI which hasn't updated yet, you can find GGMLs compatible with the older llama.cpp code in branch `previous_llama`
|
| 31 |
|
| 32 |
+
|
| 33 |
+
|
| 34 |
## Provided files
|
| 35 |
| Name | Quant method | Bits | Size | RAM required | Use case |
|
| 36 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|