mradermacher commited on
Commit
4379b23
1 Parent(s): 948afb2

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md CHANGED
@@ -1,6 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/ChuckMcSneed/dolphin-2.9.1-dbrx-llamacppfixed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ChuckMcSneed/dolphin-2.9.1-dbrx-llamacppfixed
3
+ datasets:
4
+ - cognitivecomputations/Dolphin-2.9
5
+ - teknium/OpenHermes-2.5
6
+ - m-a-p/CodeFeedback-Filtered-Instruction
7
+ - cognitivecomputations/dolphin-coder
8
+ - cognitivecomputations/samantha-data
9
+ - microsoft/orca-math-word-problems-200k
10
+ - Locutusque/function-calling-chatml
11
+ - internlm/Agent-FLAN
12
+ language:
13
+ - en
14
+ library_name: transformers
15
+ license: other
16
+ license_link: https://www.databricks.com/legal/open-model-license
17
+ license_name: databricks-open-model-license
18
+ quantized_by: mradermacher
19
+ tags:
20
+ - generated_from_trainer
21
+ - axolotl
22
+ ---
23
+ ## About
24
+
25
  <!-- ### quantize_version: 2 -->
26
  <!-- ### output_tensor_quantised: 1 -->
27
  <!-- ### convert_type: hf -->
28
  <!-- ### vocab_type: -->
29
  <!-- ### tags: -->
30
  static quants of https://huggingface.co/ChuckMcSneed/dolphin-2.9.1-dbrx-llamacppfixed
31
+
32
+ <!-- provided-files -->
33
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-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/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q2_K.gguf) | Q2_K | 48.1 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ3_XS.gguf.part2of2) | IQ3_XS | 53.9 | |
48
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ3_S.gguf.part2of2) | IQ3_S | 56.9 | beats Q3_K* |
49
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q3_K_S.gguf.part2of2) | Q3_K_S | 56.9 | |
50
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ3_M.gguf.part2of2) | IQ3_M | 58.1 | |
51
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q3_K_M.gguf.part2of2) | Q3_K_M | 63.3 | lower quality |
52
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q3_K_L.gguf.part2of2) | Q3_K_L | 68.5 | |
53
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.IQ4_XS.gguf.part2of2) | IQ4_XS | 71.0 | |
54
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q4_K_S.gguf.part2of2) | Q4_K_S | 75.0 | fast, recommended |
55
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q4_K_M.gguf.part2of2) | Q4_K_M | 80.0 | fast, recommended |
56
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q5_K_S.gguf.part2of2) | Q5_K_S | 90.7 | |
57
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q5_K_M.gguf.part2of2) | Q5_K_M | 93.7 | |
58
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q6_K.gguf.part3of3) | Q6_K | 108.1 | very good quality |
59
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.Q8_0.gguf.part3of3) | Q8_0 | 139.9 | fast, best quality |
60
+
61
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
62
+ types (lower is better):
63
+
64
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
65
+
66
+ And here are Artefact2's thoughts on the matter:
67
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
68
+
69
+ ## FAQ / Model Request
70
+
71
+ See https://huggingface.co/mradermacher/model_requests for some answers to
72
+ questions you might have and/or if you want some other model quantized.
73
+
74
+ ## Thanks
75
+
76
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
77
+ me use its servers and providing upgrades to my workstation to enable
78
+ this work in my free time.
79
+
80
+ <!-- end -->