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

README.md

@@ -18,20 +18,22 @@ This repo contains GGML files for for CPU inference using [llama.cpp](https://gi
 * [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GPTQ)
 * [Unquantised model in HF format](https://huggingface.co/TheBloke/wizardLM-7B-HF)
 
-## 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 |
 | ---- | ---- | ---- | ---- | ---- | ----- |
 `WizardLM-7B.GGML.q4_0.bin` | q4_0 | 4bit | 4.2GB | 6GB | 4bit. |
-`WizardLM-7B.GGML.q5_0.bin` | q5_0 | 5bit | 4.63GB | 7GB | Higher quality inference than 4bit, at cost of slightly higher resources. |
-`WizardLM-7B.GGML.q5_1.bin` | q5_1 | 5bit | 5.0GB | 7GB | Higher quality and resource usage again. |
+`WizardLM-7B.GGML.q4_1.bin` | q4_0 | 4bit | 4.63GB | 6GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+`WizardLM-7B.GGML.q5_0.bin` | q5_0 | 5bit | 4.63GB | 7GB | 5-bit. Higher accuracy, higher resource usage and slower inference.|
+`WizardLM-7B.GGML.q5_1.bin` | q5_1 | 5bit | 5.0GB | 7GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
+`WizardLM-7B.GGML.q8_0.bin` | q8_0 | 8bit | 8GB | 10GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
 
 ## How to run in `llama.cpp`
 
@@ -51,9 +53,7 @@ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argumen
 
 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 llama.cpp quantisation methods (May 12th)
-
-**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) to get support for thew newer files quicker.
+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 info
 
@@ -61,4 +61,4 @@ Overview of Evol-Instruct
 Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.
 
 ![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_overall.png)
-![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_running.png)
+![info](https://github.com/nlpxucan/WizardLM/raw/main/imgs/git_running.png)