mradermacher commited on
Commit
67d4c43
1 Parent(s): 42a794d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md CHANGED
@@ -1,6 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  static quants of https://huggingface.co/ExAi/dolphin-2.9-llama3-MoE-4x70B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ExAi/dolphin-2.9-llama3-MoE-4x70B
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
+ - HuggingFaceH4/ultrachat_200k
10
+ - microsoft/orca-math-word-problems-200k
11
+ - abacusai/SystemChat-1.1
12
+ - Locutusque/function-calling-chatml
13
+ - internlm/Agent-FLAN
14
+ language:
15
+ - en
16
+ library_name: transformers
17
+ license: llama3
18
+ quantized_by: mradermacher
19
+ ---
20
+ ## About
21
+
22
  <!-- ### quantize_version: 2 -->
23
  <!-- ### output_tensor_quantised: 1 -->
24
  <!-- ### convert_type: hf -->
25
  <!-- ### vocab_type: -->
26
  <!-- ### tags: nicoboss -->
27
  static quants of https://huggingface.co/ExAi/dolphin-2.9-llama3-MoE-4x70B
28
+
29
+ <!-- provided-files -->
30
+ weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
31
+ ## Usage
32
+
33
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
34
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
35
+ more details, including on how to concatenate multi-part files.
36
+
37
+ ## Provided Quants
38
+
39
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
40
+
41
+ | Link | Type | Size/GB | Notes |
42
+ |:-----|:-----|--------:|:------|
43
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q2_K.gguf.part2of2) | Q2_K | 87.7 | |
44
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_S.gguf.part3of3) | Q3_K_S | 103.7 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_M.gguf.part3of3) | Q3_K_M | 115.0 | lower quality |
46
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_L.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_L.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q3_K_L.gguf.part3of3) | Q3_K_L | 124.5 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q4_K_S.gguf.part3of3) | Q4_K_S | 136.5 | fast, recommended |
48
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q4_K_M.gguf.part3of3) | Q4_K_M | 145.0 | fast, recommended |
49
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_S.gguf.part4of4) | Q5_K_S | 165.0 | |
50
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q5_K_M.gguf.part4of4) | Q5_K_M | 170.1 | |
51
+ | [PART 1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q6_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q6_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q6_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q6_K.gguf.part4of4) | Q6_K | 196.7 | very good quality |
52
+ | [P1](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q8_0.gguf.part1of6) [P2](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q8_0.gguf.part2of6) [P3](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q8_0.gguf.part3of6) [P4](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q8_0.gguf.part4of6) [P5](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q8_0.gguf.part5of6) [P6](https://huggingface.co/mradermacher/dolphin-2.9-llama3-MoE-4x70B-GGUF/resolve/main/dolphin-2.9-llama3-MoE-4x70B.Q8_0.gguf.part6of6) | Q8_0 | 254.8 | fast, best quality |
53
+
54
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
55
+ types (lower is better):
56
+
57
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
58
+
59
+ And here are Artefact2's thoughts on the matter:
60
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
61
+
62
+ ## FAQ / Model Request
63
+
64
+ See https://huggingface.co/mradermacher/model_requests for some answers to
65
+ questions you might have and/or if you want some other model quantized.
66
+
67
+ ## Thanks
68
+
69
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
70
+ me use its servers and providing upgrades to my workstation to enable
71
+ 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.
72
+
73
+ <!-- end -->