Update README.md

README.md

@@ -1,6 +1,8 @@
 ---
 datasets:
 - gozfarb/ShareGPT_Vicuna_unfiltered
+license: other
+inference: false
 ---
 
 # VicUnlocked-30B-LoRA GGML
@@ -11,7 +13,7 @@ The files in this repo are the result of merging the above LoRA with the origina
 
 ## Repositories available
 
-* [4-bit, 5-bit and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/VicUnlocked-30B-LoRA-GGML).
+* [4-bit, 5-bit and 8-bit GGML models for CPU (+CUDA) inference](https://huggingface.co/TheBloke/VicUnlocked-30B-LoRA-GGML).
 * [4bit's GPTQ 4-bit model for GPU inference](https://huggingface.co/TheBloke/VicUnlocked-30B-LoRA-GPTQ).
 * [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/VicUnlocked-30B-LoRA-HF).
 
@@ -24,11 +26,11 @@ I have quantised the GGML files in this repo with the latest version. Therefore
 ## Provided files
 | Name | Quant method | Bits | Size | RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-`VicUnlocked-30B-LoRA.ggml.q4_0.bin` | q4_0 | 4bit | 19GB | 21GB | 4-bit. |
-`VicUnlocked-30B-LoRA.ggml.q4_1.bin` | q4_1 | 5bit | 23GB | 25GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
-`VicUnlocked-30B-LoRA.ggml.q5_0.bin` | q5_0 | 5bit | 21GB | 23GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
-`VicUnlocked-30B-LoRA.ggml.q5_1.bin` | q5_1 | 5bit | 23GB | 25GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
-`VicUnlocked-30B-LoRA.ggml.q8_0.bin` | q8_0 | 8bit | 35GB | 37GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
+`VicUnlocked-30B-LoRA.ggml.q4_0.bin` | q4_0 | 4bit | 20.3GB | 23GB | 4-bit. |
+`VicUnlocked-30B-LoRA.ggml.q4_1.bin` | q4_1 | 5bit | 24.4GB | 27GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+`VicUnlocked-30B-LoRA.ggml.q5_0.bin` | q5_0 | 5bit | 22.4GB | 25GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
+`VicUnlocked-30B-LoRA.ggml.q5_1.bin` | q5_1 | 5bit | 24.4GB | 27GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
+`VicUnlocked-30B-LoRA.ggml.q8_0.bin` | q8_0 | 8bit | 36.6GB | 39GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
 
 ## How to run in `llama.cpp`