mradermacher commited on
Commit
0f4ac8e
·
verified ·
1 Parent(s): 2e72558

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -2,11 +2,14 @@
2
  base_model: sthenno-com/miscii-14b-1225
3
  language:
4
  - en
 
5
  library_name: transformers
 
6
  quantized_by: mradermacher
7
  tags:
8
  - mergekit
9
  - merge
 
10
  ---
11
  ## About
12
 
@@ -31,20 +34,29 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
 
34
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate |
35
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
37
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality |
38
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
 
40
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
 
41
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
42
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
 
45
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS |
46
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
47
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
 
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
2
  base_model: sthenno-com/miscii-14b-1225
3
  language:
4
  - en
5
+ - zh
6
  library_name: transformers
7
+ license: apache-2.0
8
  quantized_by: mradermacher
9
  tags:
10
  - mergekit
11
  - merge
12
+ - custom-research
13
  ---
14
  ## About
15
 
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate |
38
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate |
39
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | |
42
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
43
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
47
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
49
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
50
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS |
55
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
56
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
60
  | [GGUF](https://huggingface.co/mradermacher/miscii-14b-1225-i1-GGUF/resolve/main/miscii-14b-1225.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
61
 
62
  Here is a handy graph by ikawrakow comparing some lower-quality quant