mradermacher commited on
Commit
0bc37e4
1 Parent(s): cd68747

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md CHANGED
@@ -1,6 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/yuuko-eth/Rain-2x7B-MoE-32k-v0.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: yuuko-eth/Rain-2x7B-MoE-32k-v0.2
3
+ language:
4
+ - zh
5
+ - en
6
+ library_name: transformers
7
+ license: unknown
8
+ model_name: Rain-2x7B-MoE-32k-v0.2
9
+ prompt_template: <s> SYS_PROMPT [INST] QUERY1 [/INST] RESPONSE1 [INST] QUERY2 [/INST]
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - nlp
13
+ - chinese
14
+ - mistral
15
+ - mixtral
16
+ - traditional_chinese
17
+ - merge
18
+ - mergekit
19
+ - MediaTek-Research/Breeze-7B-Instruct-v0_1
20
+ - beowolx/CodeNinja-1.0-OpenChat-7B
21
+ - mlabonne/Marcoro14-7B-slerp
22
+ ---
23
+ ## About
24
+
25
  <!-- ### quantize_version: 2 -->
26
  <!-- ### output_tensor_quantised: 1 -->
27
  <!-- ### convert_type: hf -->
28
  <!-- ### vocab_type: -->
29
  <!-- ### tags: nicoboss -->
30
  weighted/imatrix quants of https://huggingface.co/yuuko-eth/Rain-2x7B-MoE-32k-v0.2
31
+
32
+ <!-- provided-files -->
33
+ static quants are available at https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-GGUF
34
+ ## Usage
35
+
36
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
37
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
38
+ more details, including on how to concatenate multi-part files.
39
+
40
+ ## Provided Quants
41
+
42
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
43
+
44
+ | Link | Type | Size/GB | Notes |
45
+ |:-----|:-----|--------:|:------|
46
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.8 | for the desperate |
47
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.1 | mostly desperate |
48
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ2_S.gguf) | i1-IQ2_S | 4.1 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ2_M.gguf) | i1-IQ2_M | 4.4 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.7 | IQ3_XS probably better |
56
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
57
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.3 | IQ3_S probably better |
59
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.8 | IQ3_M probably better |
60
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.0 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.4 | fast on arm, low quality |
62
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.4 | fast on arm+i8mm, low quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.4 | fast on arm+sve, low quality |
64
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q4_0.gguf) | i1-Q4_0 | 7.4 | fast, low quality |
65
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.4 | optimal size/speed/quality |
66
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.9 | fast, recommended |
67
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.0 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.2 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/Rain-2x7B-MoE-32k-v0.2-i1-GGUF/resolve/main/Rain-2x7B-MoE-32k-v0.2.i1-Q6_K.gguf) | i1-Q6_K | 10.7 | practically like static Q6_K |
70
+
71
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
72
+ types (lower is better):
73
+
74
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
75
+
76
+ And here are Artefact2's thoughts on the matter:
77
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
78
+
79
+ ## FAQ / Model Request
80
+
81
+ See https://huggingface.co/mradermacher/model_requests for some answers to
82
+ questions you might have and/or if you want some other model quantized.
83
+
84
+ ## Thanks
85
+
86
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
87
+ me use its servers and providing upgrades to my workstation to enable
88
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
89
+
90
+ <!-- end -->