mradermacher commited on
Commit
5b6d7b0
1 Parent(s): 5de558d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +71 -0
README.md CHANGED
@@ -1,6 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/maywell/Qwen2-7B-Multilingual-RP
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: maywell/Qwen2-7B-Multilingual-RP
3
+ language:
4
+ - en
5
+ - ko
6
+ - ja
7
+ - zh
8
+ - es
9
+ library_name: transformers
10
+ license: apache-2.0
11
+ quantized_by: mradermacher
12
+ ---
13
+ ## About
14
+
15
  <!-- ### quantize_version: 2 -->
16
  <!-- ### output_tensor_quantised: 1 -->
17
  <!-- ### convert_type: hf -->
18
  <!-- ### vocab_type: -->
19
  <!-- ### tags: nicoboss -->
20
  weighted/imatrix quants of https://huggingface.co/maywell/Qwen2-7B-Multilingual-RP
21
+
22
+ <!-- provided-files -->
23
+ static quants are available at https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-GGUF
24
+ ## Usage
25
+
26
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
27
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
28
+ more details, including on how to concatenate multi-part files.
29
+
30
+ ## Provided Quants
31
+
32
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
33
+
34
+ | Link | Type | Size/GB | Notes |
35
+ |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate |
38
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* |
47
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Multilingual-RP-i1-GGUF/resolve/main/Qwen2-7B-Multilingual-RP.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
57
+
58
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
59
+ types (lower is better):
60
+
61
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
62
+
63
+ And here are Artefact2's thoughts on the matter:
64
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
65
+
66
+ ## FAQ / Model Request
67
+
68
+ See https://huggingface.co/mradermacher/model_requests for some answers to
69
+ questions you might have and/or if you want some other model quantized.
70
+
71
+ ## Thanks
72
+
73
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
74
+ me use its servers and providing upgrades to my workstation to enable
75
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
76
+
77
+ <!-- end -->