mradermacher commited on
Commit
ad75784
1 Parent(s): 81e1d6a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md CHANGED
@@ -1,6 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/Azure99/blossom-v5-4b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Azure99/blossom-v5-4b
3
+ datasets:
4
+ - Azure99/blossom-chat-v3
5
+ - Azure99/blossom-math-v4
6
+ - Azure99/blossom-wizard-v3
7
+ - Azure99/blossom-orca-v3
8
+ language:
9
+ - zh
10
+ - en
11
+ library_name: transformers
12
+ license: apache-2.0
13
+ quantized_by: mradermacher
14
+ ---
15
+ ## About
16
+
17
  <!-- ### quantize_version: 2 -->
18
  <!-- ### output_tensor_quantised: 1 -->
19
  <!-- ### convert_type: hf -->
20
  <!-- ### vocab_type: -->
21
  <!-- ### tags: -->
22
  static quants of https://huggingface.co/Azure99/blossom-v5-4b
23
+
24
+ <!-- provided-files -->
25
+ 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.
26
+ ## Usage
27
+
28
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
29
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
30
+ more details, including on how to concatenate multi-part files.
31
+
32
+ ## Provided Quants
33
+
34
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
35
+
36
+ | Link | Type | Size/GB | Notes |
37
+ |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q2_K.gguf) | Q2_K | 1.7 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.IQ3_XS.gguf) | IQ3_XS | 1.9 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.IQ3_S.gguf) | IQ3_S | 2.0 | beats Q3_K* |
41
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q3_K_S.gguf) | Q3_K_S | 2.0 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.IQ3_M.gguf) | IQ3_M | 2.0 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q3_K_L.gguf) | Q3_K_L | 2.3 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.IQ4_XS.gguf) | IQ4_XS | 2.3 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q5_K_S.gguf) | Q5_K_S | 2.9 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q5_K_M.gguf) | Q5_K_M | 2.9 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q6_K.gguf) | Q6_K | 3.3 | very good quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v5-4b-GGUF/resolve/main/blossom-v5-4b.f16.gguf) | f16 | 8.0 | 16 bpw, overkill |
53
+
54
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
55
+ types (lower is better):
56
+
57
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
58
+
59
+ And here are Artefact2's thoughts on the matter:
60
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
61
+
62
+ ## FAQ / Model Request
63
+
64
+ See https://huggingface.co/mradermacher/model_requests for some answers to
65
+ questions you might have and/or if you want some other model quantized.
66
+
67
+ ## Thanks
68
+
69
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
70
+ me use its servers and providing upgrades to my workstation to enable
71
+ this work in my free time.
72
+
73
+ <!-- end -->