TheBloke commited on
Commit
3bef463
1 Parent(s): f295e0d

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -31,20 +31,20 @@ I have the following Koala model repositories available:
31
  * [GPTQ quantized 4bit 7B model in `pt` and `safetensors` formats](https://huggingface.co/TheBloke/koala-7B-GPTQ-4bit-128g)
32
  * [4-bit, 5-bit and 8-bit GGML models for `llama.cpp`](https://huggingface.co/TheBloke/koala-7B-GGML)
33
 
34
- ## REQUIRES LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!
35
 
36
- llama.cpp recently made a breaking change to its quantisation methods.
37
 
38
- I have re-quantised the GGML files in this repo. Therefore you will require llama.cpp compiled on May 12th or later (commit `b9fd7ee` or later) to use them.
39
 
40
- The previous files, which will still work in older versions of llama.cpp, can be found in branch `previous_llama`.
41
 
42
  ## How to run in `llama.cpp`
43
 
44
  I use the following command line; adjust for your tastes and needs:
45
 
46
  ```
47
- ./main -t 18 -m koala-7B-4bit-128g.GGML.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "BEGINNING OF CONVERSATION:
48
  USER: <PROMPT GOES HERE>
49
  GPT:"
50
  ```
@@ -98,4 +98,4 @@ The model weights are intended for academic research only, subject to the
98
  [model License of LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md),
99
  [Terms of Use of the data generated by OpenAI](https://openai.com/policies/terms-of-use),
100
  and [Privacy Practices of ShareGPT](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb).
101
- Any other usage of the model weights, including but not limited to commercial usage, is strictly prohibited.
 
31
  * [GPTQ quantized 4bit 7B model in `pt` and `safetensors` formats](https://huggingface.co/TheBloke/koala-7B-GPTQ-4bit-128g)
32
  * [4-bit, 5-bit and 8-bit GGML models for `llama.cpp`](https://huggingface.co/TheBloke/koala-7B-GGML)
33
 
34
+ ## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
35
 
36
+ llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
37
 
38
+ 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.
39
 
40
+ For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.
41
 
42
  ## How to run in `llama.cpp`
43
 
44
  I use the following command line; adjust for your tastes and needs:
45
 
46
  ```
47
+ ./main -t 18 -m koala-7B-4bit-128g.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "BEGINNING OF CONVERSATION:
48
  USER: <PROMPT GOES HERE>
49
  GPT:"
50
  ```
 
98
  [model License of LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md),
99
  [Terms of Use of the data generated by OpenAI](https://openai.com/policies/terms-of-use),
100
  and [Privacy Practices of ShareGPT](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb).
101
+ Any other usage of the model weights, including but not limited to commercial usage, is strictly prohibited.