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

README.md

@@ -32,28 +32,29 @@ This model works best with the following prompt template:
 ### Assistant:
 ```
 
-## REQUIRES LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!
+## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
 
-llama.cpp recently made a breaking change to its quantisation methods.
+llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
 
-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.
+I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 12th or later (commit `b9fd7ee` or later) to use them.
 
-The previous files, which will still work in older versions of llama.cpp, can be found in branch `previous_llama`.
+For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.
 
 ## Provided files
 | Name | Quant method | Bits | Size | RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-`stable-vicuna-13B.ggml.q4_0.bin` | q4_0 | 4bit | 8.14GB | 10.5GB | 4bit. |
-`stable-vicuna-13B.ggml.q5_0.bin` | q5_0 | 5bit | 8.95GB | 11.0GB | 5bit. Higher accuracy, higher resource usage and slower inference. |
-`stable-vicuna-13B.ggml.q5_1.bin` | q5_1 | 5bit | 9.76GB | 12.25GB | 5bit. Higher accuracy than q5_0, but again higher resource usage and slower inference. |
-`stable-vicuna-13B.ggml.q8_0.bin` | q8_0 | 8bit | 14.6GB | 17GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
+`stable-vicuna-13B.ggmlv3.q4_0.bin` | q4_0 | 4bit | 8.14GB | 10.5GB | 4bit. |
+`stable-vicuna-13B.ggmlv3.q4_1.bin` | q4_1 | 4bit | 8.95GB | 11.0GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+`stable-vicuna-13B.ggmlv3.q5_0.bin` | q5_0 | 5bit | 8.95GB | 11.0GB | 5bit. Higher accuracy, higher resource usage and slower inference. |
+`stable-vicuna-13B.ggmlv3.q5_1.bin` | q5_1 | 5bit | 9.76GB | 12.25GB | 5bit. Higher accuracy than q5_0, but again higher resource usage and slower inference. |
+`stable-vicuna-13B.ggmlv3.q8_0.bin` | q8_0 | 8bit | 14.6GB | 17GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
 
 ## How to run in `llama.cpp`
 
 I use the following command line; adjust for your tastes and needs:
 
 ```
-./main -t 18 -m stable-vicuna-13B.ggml.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -r "### Human:" -p "### Human: write a story about llamas ### Assistant:"
+./main -t 18 -m stable-vicuna-13B.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -r "### Human:" -p "### Human: write a story about llamas ### Assistant:"
 ```
 
 Change `-t 18` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
@@ -64,7 +65,7 @@ GGML models can be loaded into text-generation-webui by installing the llama.cpp
 
 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 May 12th updated quantisation methods.
+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.
 
 **Thireus** has written a [great guide on how to update it to the latest llama.cpp code](https://huggingface.co/TheBloke/wizardLM-7B-GGML/discussions/5) which may help with getting the files working in text-gen-ui sooner.