mradermacher commited on
Commit
1a74188
1 Parent(s): 72bde53

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +68 -0
README.md CHANGED
@@ -1,5 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hfhfix -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/jsfs11/Llama-3-RPMerge-8B-SLERP
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: jsfs11/Llama-3-RPMerge-8B-SLERP
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ tags:
8
+ - merge
9
+ - mergekit
10
+ - lazymergekit
11
+ - Undi95/Llama-3-LewdPlay-8B-evo
12
+ - cgato/L3-TheSpice-8b-v0.8.3
13
+ ---
14
+ ## About
15
+
16
  <!-- ### quantize_version: 2 -->
17
  <!-- ### output_tensor_quantised: 1 -->
18
  <!-- ### convert_type: hfhfix -->
19
  <!-- ### vocab_type: -->
20
  static quants of https://huggingface.co/jsfs11/Llama-3-RPMerge-8B-SLERP
21
+
22
+
23
+ <!-- provided-files -->
24
+ 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.
25
+ ## Usage
26
+
27
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
28
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
29
+ more details, including on how to concatenate multi-part files.
30
+
31
+ ## Provided Quants
32
+
33
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
34
+
35
+ | Link | Type | Size/GB | Notes |
36
+ |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q2_K.gguf) | Q2_K | 3.3 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
41
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.IQ3_M.gguf) | IQ3_M | 3.9 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-RPMerge-8B-SLERP-GGUF/resolve/main/Llama-3-RPMerge-8B-SLERP.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
52
+
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.
72
+
73
+ <!-- end -->