Transformers
GGUF
imatrix
conversational
leonardlin commited on
Commit
dc8ea1f
·
verified ·
1 Parent(s): fdc8df3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -24,16 +24,16 @@ This repo contains select GGUF quants of [shisa-ai/shisa-v2-llama3.1-405b](https
24
 
25
  | Type | Size (GB) |
26
  |:--------|----------:|
27
- | IQ2_XXS | 155 |
28
  | IQ3_XS | 155 |
29
  | IQ3_M | 170 |
30
  | IQ4_XS | 202 |
31
  | Q4_K_M | 227 |
32
  | Q8_0 | 402 |
33
 
34
- Graph by ikawrakow comparing some lower-quality quant PPL (lower is better) - via mradermacher:
35
 
36
- ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
37
 
38
  ## Making Quants
39
  ```
 
24
 
25
  | Type | Size (GB) |
26
  |:--------|----------:|
27
+ | IQ2_XXS | 100 |
28
  | IQ3_XS | 155 |
29
  | IQ3_M | 170 |
30
  | IQ4_XS | 202 |
31
  | Q4_K_M | 227 |
32
  | Q8_0 | 402 |
33
 
34
+ Graph by ikawrakow comparing some lower-quality quant PPL (lower is better):
35
 
36
+ ![image.png](quantpplgraph.png)
37
 
38
  ## Making Quants
39
  ```