mradermacher commited on
Commit
3dd539a
1 Parent(s): ba96420

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: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/HiroseKoichi/Llama-3-8B-Stroganoff-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HiroseKoichi/Llama-3-8B-Stroganoff-2.0
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: llama3
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - nsfw
10
+ - not-for-all-audiences
11
+ - llama-3
12
+ - text-generation-inference
13
+ - mergekit
14
+ - merge
15
+ ---
16
+ ## About
17
+
18
  <!-- ### quantize_version: 2 -->
19
  <!-- ### output_tensor_quantised: 1 -->
20
  <!-- ### convert_type: hf -->
21
  <!-- ### vocab_type: -->
22
  <!-- ### tags: nicoboss -->
23
  weighted/imatrix quants of https://huggingface.co/HiroseKoichi/Llama-3-8B-Stroganoff-2.0
24
+
25
+ <!-- provided-files -->
26
+ static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-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/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-2.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-2.0.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
79
+
80
+ <!-- end -->