Transformers
GGUF
English
reasoning
Inference Endpoints
mradermacher commited on
Commit
66c5d9f
1 Parent(s): bad83ae

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -1
README.md CHANGED
@@ -21,7 +21,6 @@ tags:
21
  <!-- ### vocab_type: -->
22
  weighted/imatrix quants of https://huggingface.co/jukofyork/Eurus-70b-sft-fixed
23
 
24
-
25
  <!-- provided-files -->
26
  static quants are available at https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-GGUF
27
  ## Usage
@@ -36,8 +35,27 @@ more details, including on how to concatenate multi-part files.
36
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
 
 
 
 
 
 
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
 
 
 
 
41
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
21
  <!-- ### vocab_type: -->
22
  weighted/imatrix quants of https://huggingface.co/jukofyork/Eurus-70b-sft-fixed
23
 
 
24
  <!-- provided-files -->
25
  static quants are available at https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-GGUF
26
  ## Usage
 
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ1_S.gguf) | i1-IQ1_S | 14.6 | for the desperate |
39
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | for the desperate |
40
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
48
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | |
58
+ | [PART 1](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | practically like static Q6_K |
59
 
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant