Update GGML models for latest ggml commit with ggml version included.

README.md

@@ -26,12 +26,12 @@ Please note that these MPT GGMLs are **not compatbile with llama.cpp**. Right no
 ## Provided files
 | Name | Quant method | Bits | Size | RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-`mpt7b-instruct.ggmlv2.q4_0.bin` | q4_0 | 4bit | 4.16GB | 6.2GB | 4-bit. |
-`mpt7b-instruct.ggmlv2.q4_1.bin` | q4_0 | 4bit | 4.99GB | 7.2GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
-`mpt7b-instruct.ggmlv2.q5_0.bin` | q5_0 | 5bit | 4.57GB | 6.8GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
-`mpt7b-instruct.ggmlv2.q5_1.bin` | q5_1 | 5bit | 4.99GB | 7.2GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
-`mpt7b-instruct.ggmlv2.q8_0.bin` | q8_0 | 8bit | 7.48GB | 9.7GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
-`mpt7b-instruct.ggmlv2.fp16.bin` | fp16 | 16bit | 13.30GB | 16GB | Full 16-bit. |
+`mpt7b-instruct.ggmlv3.q4_0.bin` | q4_0 | 4bit | 4.16GB | 6.2GB | 4-bit. |
+`mpt7b-instruct.ggmlv3.q4_1.bin` | q4_0 | 4bit | 4.99GB | 7.2GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+`mpt7b-instruct.ggmlv3.q5_0.bin` | q5_0 | 5bit | 4.57GB | 6.8GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
+`mpt7b-instruct.ggmlv3.q5_1.bin` | q5_1 | 5bit | 4.99GB | 7.2GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
+`mpt7b-instruct.ggmlv3.q8_0.bin` | q8_0 | 8bit | 7.48GB | 9.7GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
+`mpt7b-instruct.ggmlv3.fp16.bin` | fp16 | 16bit | 13.30GB | 16GB | Full 16-bit. |
 
 ## Compatibilty
 
@@ -52,7 +52,7 @@ mkdir build
 cd build
 cmake ..
 cmake --build . --config Release
-bin/mpt -m /path/to/mpt7b-instruct.ggmlv2.q4_0.bin -t 8 -n 512 -p "Write a story about llamas"
+bin/mpt -m /path/to/mpt7b-instruct.ggmlv3.q4_0.bin -t 8 -n 512 -p "Write a story about llamas"
 ```
 
 Please see the ggml repo for other build options.