Update README.md

README.md

@@ -21,11 +21,11 @@ This repo contains GGML files for for CPU inference using [llama.cpp](https://gi
 ## Provided files
 | Name | Quant method | Bits | Size | RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-`WizardLM-7B.GGML.q4_0.bin` | q4_0 | 4bit | 4.0GB | 6GB | Maximum compatibility |
-`WizardLM-7B.GGML.q4_2.bin` | q4_2 | 4bit | 4.0GB | 6GB | Best compromise between resources, speed and quality |
-`WizardLM-7B.GGML.q4_3.bin` | q4_3 | 4bit | 4.8GB | 7GB | Maximum quality 4bit, higher RAM requirements and slower inference |
-`WizardLM-7B.GGML.q5_0.bin` | q5_0 | 5bit | 4.4GB | 7GB | Brand new 5bit method. Potentially higher quality than 4bit, at cost of slightly higher resources. |
-`WizardLM-7B.GGML.q5_1.bin` | q5_1 | 5bit | 4.8GB | 7GB | Brand new 5bit method. Slightly higher resource usage than q5_0.|
+`WizardLM-7B.GGML.q4_0.bin` | q4_0 | 4bit | 4.2GB | 6GB | Maximum compatibility |
+`WizardLM-7B.GGML.q4_2.bin` | q4_2 | 4bit | 4.2GB | 6GB | Best compromise between resources, speed and quality |
+`WizardLM-7B.GGML.q4_3.bin` | q4_3 | 4bit | 5.0GB | 7GB | Maximum quality 4bit, higher RAM requirements and slower inference |
+`WizardLM-7B.GGML.q5_0.bin` | q5_0 | 5bit | 4.63GB | 7GB | Brand new 5bit method. Potentially higher quality than 4bit, at cost of slightly higher resources. |
+`WizardLM-7B.GGML.q5_1.bin` | q5_1 | 5bit | 5.0GB | 7GB | Brand new 5bit method. Slightly higher resource usage than q5_0.|
 
 * The q4_0 file provides lower quality, but maximal compatibility. It will work with past and future versions of llama.cpp
 * The q4_2 file offers the best combination of performance and quality. This format is still subject to change and there may be compatibility issues, see below.