Hugging Face's logo

mradermacher
/
Llama-SEA-LION-v3.5-70B-R-i1-GGUF

Transformers
GGUF
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
e765194
·
verified ·
1 Parent(s): e9f58b7

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md CHANGED
@@ -1,6 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/aisingapore/Llama-SEA-LION-v3.5-70B-R
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: aisingapore/Llama-SEA-LION-v3.5-70B-R
3
+ language:
4
+ - en
5
+ - zh
6
+ - vi
7
+ - id
8
+ - th
9
+ - fil
10
+ - ta
11
+ - ms
12
+ - km
13
+ - lo
14
+ - my
15
+ - jv
16
+ - su
17
+ library_name: transformers
18
+ license: llama3.1
19
+ quantized_by: mradermacher
20
+ ---
21
+ ## About
22
+
23
  <!-- ### quantize_version: 2 -->
24
  <!-- ### output_tensor_quantised: 1 -->
25
  <!-- ### convert_type: hf -->
26
  <!-- ### vocab_type: -->
27
  <!-- ### tags: nicoboss -->
28
  weighted/imatrix quants of https://huggingface.co/aisingapore/Llama-SEA-LION-v3.5-70B-R
29
+
30
+ <!-- provided-files -->
31
+ static quants are available at https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-GGUF
32
+ ## Usage
33
+
34
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
35
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
36
+ more details, including on how to concatenate multi-part files.
37
+
38
+ ## Provided Quants
39
+
40
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
41
+
42
+ | Link | Type | Size/GB | Notes |
43
+ |:-----|:-----|--------:|:------|
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
45
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
46
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
55
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
56
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
58
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
59
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
61
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
62
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
63
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q4_1.gguf) | i1-Q4_1 | 44.4 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
66
+ | [PART 1](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-SEA-LION-v3.5-70B-R-i1-GGUF/resolve/main/Llama-SEA-LION-v3.5-70B-R.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
67
+
68
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
69
+ types (lower is better):
70
+
71
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
72
+
73
+ And here are Artefact2's thoughts on the matter:
74
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
75
+
76
+ ## FAQ / Model Request
77
+
78
+ See https://huggingface.co/mradermacher/model_requests for some answers to
79
+ questions you might have and/or if you want some other model quantized.
80
+
81
+ ## Thanks
82
+
83
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
84
+ me use its servers and providing upgrades to my workstation to enable
85
+ 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.
86
+
87
+ <!-- end -->