mradermacher commited on
Commit
95c6741
1 Parent(s): 9b91e1d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md CHANGED
@@ -1,6 +1,66 @@
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: grimulkan/aurelian-v0.5-70b-rope8-32K-fp16
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: unknown
7
+ quantized_by: mradermacher
8
+ ---
9
+ ## About
10
+
11
  <!-- ### quantize_version: 2 -->
12
  <!-- ### output_tensor_quantised: 1 -->
13
  <!-- ### convert_type: hf -->
14
  <!-- ### vocab_type: -->
15
  <!-- ### tags: -->
16
  static quants of https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16
17
+
18
+ <!-- provided-files -->
19
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-i1-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/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q2_K.gguf) | Q2_K | 25.6 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
35
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.IQ3_M.gguf) | IQ3_M | 31.0 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
44
+ | [PART 1](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
45
+ | [PART 1](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/aurelian-v0.5-70b-rope8-32K-fp16-GGUF/resolve/main/aurelian-v0.5-70b-rope8-32K-fp16.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
46
+
47
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
48
+ types (lower is better):
49
+
50
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
51
+
52
+ And here are Artefact2's thoughts on the matter:
53
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
54
+
55
+ ## FAQ / Model Request
56
+
57
+ See https://huggingface.co/mradermacher/model_requests for some answers to
58
+ questions you might have and/or if you want some other model quantized.
59
+
60
+ ## Thanks
61
+
62
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
63
+ me use its servers and providing upgrades to my workstation to enable
64
+ this work in my free time.
65
+
66
+ <!-- end -->