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

README.md

@@ -26,20 +26,22 @@ This model requires 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 19th or later (commit `2d5db48` 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 |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-`OpenAssistant-30B-epoch7.ggml.q4_0.bin` | q4_0 | 4bit | 20.3GB | 23GB | 4-bit. |
-`OpenAssistant-30B-epoch7.ggml.q5_0.bin` | q5_0 | 5bit | 22.4GB | 25GB | 5-bit. Higher accuracy, higher resource usage and slower inference.  |
-`OpenAssistant-30B-epoch7.ggml.q5_1.bin` | q5_1 | 5bit | 24.4GB | 27GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
+`OpenAssistant-30B-epoch7.ggmlv3.q4_0.bin` | q4_0 | 4bit | 20.3GB | 23GB | 4-bit. |
+`OpenAssistant-30B-epoch7.ggmlv3.q4_1.bin` | q4_1 | 4bit | 22.4GB | 25GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+`OpenAssistant-30B-epoch7.ggmlv3.q5_0.bin` | q5_0 | 5bit | 22.4GB | 25GB | 5-bit. Higher accuracy, higher resource usage and slower inference.  |
+`OpenAssistant-30B-epoch7.ggmlv3.q5_1.bin` | q5_1 | 5bit | 24.4GB | 27GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
+`OpenAssistant-30B-epoch7.ggmlv3.q8_9.bin` | q8_0 | 8bit | 24.4GB | 27GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use.|
 
 
 ## How to run in `llama.cpp`
@@ -47,7 +49,7 @@ The previous files, which will still work in older versions of llama.cpp, can be
 I use the following command line; adjust for your tastes and needs:
 
 ```
-./main -t 18 -m OpenAssistant-30B-epoch7.ggml.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|prompter|>Write a very story about llamas <|assistant|>:"
+./main -t 18 -m OpenAssistant-30B-epoch7.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|prompter|>Write a very 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`.
@@ -109,4 +111,4 @@ llama-30b-sft-7:
         max_val_set: 250
 ```
 
-- **OASST dataset paper:** https://arxiv.org/abs/2304.07327
+- **OASST dataset paper:** https://arxiv.org/abs/2304.07327