Transformers
GGUF
English
Not-For-All-Audiences
Inference Endpoints
conversational
mradermacher commited on
Commit
c5d5103
1 Parent(s): 3a210f6

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: -->
6
  static quants of https://huggingface.co/crestf411/L3.1-70B-sunfall-v0.6.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: crestf411/L3.1-70B-sunfall-v0.6.1
3
+ datasets:
4
+ - crestf411/LimaRP-DS
5
+ - AI-MO/NuminaMath-CoT
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ license: llama3
10
+ license_link: LICENSE
11
+ license_name: llama3
12
+ quantized_by: mradermacher
13
+ tags:
14
+ - not-for-all-audiences
15
+ ---
16
+ ## About
17
+
18
  <!-- ### quantize_version: 2 -->
19
  <!-- ### output_tensor_quantised: 1 -->
20
  <!-- ### convert_type: hf -->
21
  <!-- ### vocab_type: -->
22
  <!-- ### tags: -->
23
  static quants of https://huggingface.co/crestf411/L3.1-70B-sunfall-v0.6.1
24
+
25
+ <!-- provided-files -->
26
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-i1-GGUF
27
+ ## Usage
28
+
29
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
30
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
31
+ more details, including on how to concatenate multi-part files.
32
+
33
+ ## Provided Quants
34
+
35
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
36
+
37
+ | Link | Type | Size/GB | Notes |
38
+ |:-----|:-----|--------:|:------|
39
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q2_K.gguf) | Q2_K | 26.5 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.IQ3_XS.gguf) | IQ3_XS | 29.4 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
42
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.IQ3_M.gguf) | IQ3_M | 32.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
51
+ | [PART 1](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
52
+ | [PART 1](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/L3.1-70B-sunfall-v0.6.1-GGUF/resolve/main/L3.1-70B-sunfall-v0.6.1.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | 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.
72
+
73
+ <!-- end -->