mradermacher commited on
Commit
7bef2db
1 Parent(s): 9191b48

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -37,19 +37,30 @@ more details, including on how to concatenate multi-part files.
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
 
40
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
41
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | |
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 4.7 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.5 | IQ3_S probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.1 | IQ3_M probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
 
 
 
 
51
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.6 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
 
 
53
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
37
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate |
41
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
42
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 4.7 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* |
51
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.5 | IQ3_S probably better |
54
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.1 | IQ3_M probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.5 | fast on arm, low quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.5 | fast on arm+i8mm, low quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.5 | fast on arm+sve, low quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
60
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.6 | optimal size/speed/quality |
61
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
62
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.4 | |
64
  | [GGUF](https://huggingface.co/mradermacher/Ziya2-13B-Base-i1-GGUF/resolve/main/Ziya2-13B-Base.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
65
 
66
  Here is a handy graph by ikawrakow comparing some lower-quality quant