mradermacher commited on
Commit
b168c35
1 Parent(s): 8475b86

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md CHANGED
@@ -1,6 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
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/GeneZC/MiniChat-1.5-3B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: GeneZC/MiniChat-1.5-3B
3
+ language:
4
+ - en
5
+ - zh
6
+ library_name: transformers
7
+ license: apache-2.0
8
+ quantized_by: mradermacher
9
+ ---
10
+ ## About
11
+
12
  <!-- ### quantize_version: 2 -->
13
  <!-- ### output_tensor_quantised: 1 -->
14
  <!-- ### convert_type: hf -->
15
  <!-- ### vocab_type: -->
16
  <!-- ### tags: -->
17
  static quants of https://huggingface.co/GeneZC/MiniChat-1.5-3B
18
+
19
+ <!-- provided-files -->
20
+ 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.
21
+ ## Usage
22
+
23
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
24
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
25
+ more details, including on how to concatenate multi-part files.
26
+
27
+ ## Provided Quants
28
+
29
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
30
+
31
+ | Link | Type | Size/GB | Notes |
32
+ |:-----|:-----|--------:|:------|
33
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q2_K.gguf) | Q2_K | 1.3 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.IQ3_XS.gguf) | IQ3_XS | 1.4 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.IQ3_S.gguf) | IQ3_S | 1.5 | beats Q3_K* |
36
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q3_K_S.gguf) | Q3_K_S | 1.5 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.IQ3_M.gguf) | IQ3_M | 1.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q3_K_L.gguf) | Q3_K_L | 1.7 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.IQ4_XS.gguf) | IQ4_XS | 1.8 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q5_K_S.gguf) | Q5_K_S | 2.2 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.Q8_0.gguf) | Q8_0 | 3.3 | fast, best quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/MiniChat-1.5-3B-GGUF/resolve/main/MiniChat-1.5-3B.f16.gguf) | f16 | 6.1 | 16 bpw, overkill |
48
+
49
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
50
+ types (lower is better):
51
+
52
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
53
+
54
+ And here are Artefact2's thoughts on the matter:
55
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
56
+
57
+ ## FAQ / Model Request
58
+
59
+ See https://huggingface.co/mradermacher/model_requests for some answers to
60
+ questions you might have and/or if you want some other model quantized.
61
+
62
+ ## Thanks
63
+
64
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
65
+ me use its servers and providing upgrades to my workstation to enable
66
+ this work in my free time.
67
+
68
+ <!-- end -->