mradermacher commited on
Commit
3ca040a
1 Parent(s): 48848d3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -0
README.md CHANGED
@@ -1,5 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/Qwen/Qwen1.5-110B-Chat
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen1.5-110B-Chat
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: other
7
+ license_link: https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE
8
+ license_name: tongyi-qianwen
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - chat
12
+ ---
13
+ ## About
14
+
15
  <!-- ### quantize_version: 2 -->
16
  <!-- ### output_tensor_quantised: 1 -->
17
  <!-- ### convert_type: hf -->
18
  <!-- ### vocab_type: -->
19
  static quants of https://huggingface.co/Qwen/Qwen1.5-110B-Chat
20
+
21
+ <!-- provided-files -->
22
+ weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
23
+ ## Usage
24
+
25
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
26
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
27
+ more details, including on how to concatenate multi-part files.
28
+
29
+ ## Provided Quants
30
+
31
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
32
+
33
+ | Link | Type | Size/GB | Notes |
34
+ |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-GGUF/resolve/main/Qwen1.5-110B-Chat.IQ3_S.gguf) | IQ3_S | 48.6 | beats Q3_K* |
36
+ | [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-GGUF/resolve/main/Qwen1.5-110B-Chat.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-GGUF/resolve/main/Qwen1.5-110B-Chat.Q4_K_S.gguf.part2of2) | Q4_K_S | 63.6 | fast, recommended |
37
+ | [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-GGUF/resolve/main/Qwen1.5-110B-Chat.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-GGUF/resolve/main/Qwen1.5-110B-Chat.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-GGUF/resolve/main/Qwen1.5-110B-Chat.Q8_0.gguf.part3of3) | Q8_0 | 118.3 | fast, best quality |
38
+
39
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
40
+ types (lower is better):
41
+
42
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
43
+
44
+ And here are Artefact2's thoughts on the matter:
45
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
46
+
47
+ ## FAQ / Model Request
48
+
49
+ See https://huggingface.co/mradermacher/model_requests for some answers to
50
+ questions you might have and/or if you want some other model quantized.
51
+
52
+ ## Thanks
53
+
54
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
55
+ me use its servers and providing upgrades to my workstation to enable
56
+ this work in my free time.
57
+
58
+ <!-- end -->