Hugging Face's logo

mradermacher
/
Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF

Transformers
GGUF
English
Merge
programming
code generation
code
codeqwen
coding
coder
qwen2
chat
qwen
qwen-coder
brainstorm
brainstorm20x
microsoft
nextcoder
selekt
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
9cb8ad7
·
verified ·
1 Parent(s): 481186f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +99 -0
README.md CHANGED
@@ -1,6 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B
3
+ datasets:
4
+ - microsoft/NextCoderDataset
5
+ - microsoft/NextCoderDataset-Conversational
6
+ - bigcode/commitpackft
7
+ - bigcode/starcoderdata
8
+ language:
9
+ - en
10
+ library_name: transformers
11
+ license: apache-2.0
12
+ mradermacher:
13
+ readme_rev: 1
14
+ quantized_by: mradermacher
15
+ tags:
16
+ - merge
17
+ - programming
18
+ - code generation
19
+ - code
20
+ - codeqwen
21
+ - coding
22
+ - coder
23
+ - qwen2
24
+ - chat
25
+ - qwen
26
+ - qwen-coder
27
+ - code
28
+ - chat
29
+ - brainstorm
30
+ - brainstorm20x
31
+ - microsoft
32
+ - nextcoder
33
+ - selekt
34
+ ---
35
+ ## About
36
+
37
  <!-- ### quantize_version: 2 -->
38
  <!-- ### output_tensor_quantised: 1 -->
39
  <!-- ### convert_type: hf -->
40
  <!-- ### vocab_type: -->
41
  <!-- ### tags: nicoboss -->
42
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B
43
+
44
+ <!-- provided-files -->
45
+
46
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF).***
47
+
48
+ static quants are available at https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-GGUF
49
+ ## Usage
50
+
51
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
52
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
53
+ more details, including on how to concatenate multi-part files.
54
+
55
+ ## Provided Quants
56
+
57
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
58
+
59
+ | Link | Type | Size/GB | Notes |
60
+ |:-----|:-----|--------:|:------|
61
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.9 | for the desperate |
62
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.1 | mostly desperate |
63
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.5 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.0 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.3 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.4 | very low quality |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.7 | IQ3_XXS probably better |
69
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.9 | lower quality |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.2 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.5 | IQ3_XS probably better |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.5 | beats Q3_K* |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.6 | |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.0 | IQ3_S probably better |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.5 | IQ3_M probably better |
76
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.7 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.0 | prefer IQ4_XS |
78
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.0 | fast, low quality |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.1 | optimal size/speed/quality |
80
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.4 | fast, recommended |
81
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.7 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.5 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.7 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B-i1-GGUF/resolve/main/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-128k-ctx-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.0 | practically like static Q6_K |
85
+
86
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
87
+ types (lower is better):
88
+
89
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
90
+
91
+ And here are Artefact2's thoughts on the matter:
92
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
93
+
94
+ ## FAQ / Model Request
95
+
96
+ See https://huggingface.co/mradermacher/model_requests for some answers to
97
+ questions you might have and/or if you want some other model quantized.
98
+
99
+ ## Thanks
100
+
101
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
102
+ me use its servers and providing upgrades to my workstation to enable
103
+ 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.
104
+
105
+ <!-- end -->