Hugging Face's logo

mradermacher
/
Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF

Transformers
GGUF
English
Merge
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
mixture of experts
qwen2moe
2X7B
shared expert
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
9d7571c
·
verified ·
1 Parent(s): 68c2762

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md CHANGED
@@ -1,6 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/DavidAU/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ mradermacher:
8
+ readme_rev: 1
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - merge
12
+ - programming
13
+ - code generation
14
+ - code
15
+ - codeqwen
16
+ - moe
17
+ - coding
18
+ - coder
19
+ - qwen2
20
+ - chat
21
+ - qwen
22
+ - qwen-coder
23
+ - mixture of experts
24
+ - qwen2moe
25
+ - 2X7B
26
+ - shared expert
27
+ ---
28
+ ## About
29
+
30
  <!-- ### quantize_version: 2 -->
31
  <!-- ### output_tensor_quantised: 1 -->
32
  <!-- ### convert_type: hf -->
33
  <!-- ### vocab_type: -->
34
  <!-- ### tags: nicoboss -->
35
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B
36
+
37
+ <!-- provided-files -->
38
+
39
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF).***
40
+
41
+ static quants are available at https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-GGUF
42
+ ## Usage
43
+
44
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
45
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
46
+ more details, including on how to concatenate multi-part files.
47
+
48
+ ## Provided Quants
49
+
50
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
51
+
52
+ | Link | Type | Size/GB | Notes |
53
+ |:-----|:-----|--------:|:------|
54
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.3 | for the desperate |
55
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.7 | mostly desperate |
56
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.3 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.9 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ2_S.gguf) | i1-IQ2_S | 6.0 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ2_M.gguf) | i1-IQ2_M | 6.5 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 6.8 | very low quality |
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q2_K.gguf) | i1-Q2_K | 7.2 | IQ3_XXS probably better |
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.6 | lower quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.1 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.5 | IQ3_XS probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ3_S.gguf) | i1-IQ3_S | 8.5 | beats Q3_K* |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ3_M.gguf) | i1-IQ3_M | 8.6 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.3 | IQ3_S probably better |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.1 | IQ3_M probably better |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.4 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q4_0.gguf) | i1-Q4_0 | 11.0 | fast, low quality |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.0 | optimal size/speed/quality |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 11.7 | fast, recommended |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q4_1.gguf) | i1-Q4_1 | 12.1 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 13.3 | |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 13.6 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B-i1-GGUF/resolve/main/Qwen2.5-2X7B-Coder-Soar-qwen-Coder-Instruct-OlympicCoder-19B.i1-Q6_K.gguf) | i1-Q6_K | 15.7 | practically like static Q6_K |
77
+
78
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
79
+ types (lower is better):
80
+
81
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
82
+
83
+ And here are Artefact2's thoughts on the matter:
84
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
85
+
86
+ ## FAQ / Model Request
87
+
88
+ See https://huggingface.co/mradermacher/model_requests for some answers to
89
+ questions you might have and/or if you want some other model quantized.
90
+
91
+ ## Thanks
92
+
93
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
94
+ me use its servers and providing upgrades to my workstation to enable
95
+ 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.
96
+
97
+ <!-- end -->