mradermacher commited on
Commit
0cefe7f
1 Parent(s): 49f4b75

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md CHANGED
@@ -1,5 +1,67 @@
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  weighted/imatrix quants of https://huggingface.co/uncensorie/chronob-1.4-lin-70b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: uncensorie/chronob-1.4-lin-70b
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: llama2
7
+ quantized_by: mradermacher
8
+ ---
9
+ ## About
10
+
11
  <!-- ### quantize_version: 1 -->
12
  <!-- ### output_tensor_quantised: 1 -->
13
  <!-- ### convert_type: -->
14
  <!-- ### vocab_type: -->
15
  weighted/imatrix quants of https://huggingface.co/uncensorie/chronob-1.4-lin-70b
16
+
17
+
18
+ <!-- provided-files -->
19
+ static quants are available at https://huggingface.co/mradermacher/chronob-1.4-lin-70b-GGUF
20
+ ## Usage
21
+
22
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
23
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
24
+ more details, including on how to concatenate multi-part files.
25
+
26
+ ## Provided Quants
27
+
28
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
29
+
30
+ | Link | Type | Size/GB | Notes |
31
+ |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
37
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
40
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
44
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | |
50
+ | [PART 1](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/chronob-1.4-lin-70b-i1-GGUF/resolve/main/chronob-1.4-lin-70b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | practically like static Q6_K |
51
+
52
+
53
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
54
+ types (lower is better):
55
+
56
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
57
+
58
+ And here are Artefact2's thoughts on the matter:
59
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
60
+
61
+ ## Thanks
62
+
63
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
64
+ me use its servers and providing upgrades to my workstation to enable
65
+ this work in my free time.
66
+
67
+ <!-- end -->