mradermacher commited on
Commit
99c1499
1 Parent(s): 8e51273

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md CHANGED
@@ -1,6 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/mervinpraison/tamilan-2-27b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mervinpraison/tamilan-2-27b
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - text-generation-inference
10
+ - transformers
11
+ - unsloth
12
+ - gemma2
13
+ - trl
14
+ - sft
15
+ - praisonai
16
+ - praison
17
+ ---
18
+ ## About
19
+
20
  <!-- ### quantize_version: 2 -->
21
  <!-- ### output_tensor_quantised: 1 -->
22
  <!-- ### convert_type: hf -->
23
  <!-- ### vocab_type: -->
24
  <!-- ### tags: -->
25
  static quants of https://huggingface.co/mervinpraison/tamilan-2-27b
26
+
27
+ <!-- provided-files -->
28
+ 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.
29
+ ## Usage
30
+
31
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
32
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
33
+ more details, including on how to concatenate multi-part files.
34
+
35
+ ## Provided Quants
36
+
37
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
38
+
39
+ | Link | Type | Size/GB | Notes |
40
+ |:-----|:-----|--------:|:------|
41
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q2_K.gguf) | Q2_K | 10.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.IQ3_XS.gguf) | IQ3_XS | 11.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.IQ3_S.gguf) | IQ3_S | 12.3 | beats Q3_K* |
44
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q3_K_S.gguf) | Q3_K_S | 12.3 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.IQ3_M.gguf) | IQ3_M | 12.6 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q3_K_M.gguf) | Q3_K_M | 13.5 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q3_K_L.gguf) | Q3_K_L | 14.6 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.IQ4_XS.gguf) | IQ4_XS | 15.0 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q4_K_S.gguf) | Q4_K_S | 15.8 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q4_K_M.gguf) | Q4_K_M | 16.7 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q5_K_S.gguf) | Q5_K_S | 19.0 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q5_K_M.gguf) | Q5_K_M | 19.5 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q6_K.gguf) | Q6_K | 22.4 | very good quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-GGUF/resolve/main/tamilan-2-27b.Q8_0.gguf) | Q8_0 | 29.0 | fast, best quality |
55
+
56
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
57
+ types (lower is better):
58
+
59
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
60
+
61
+ And here are Artefact2's thoughts on the matter:
62
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
63
+
64
+ ## FAQ / Model Request
65
+
66
+ See https://huggingface.co/mradermacher/model_requests for some answers to
67
+ questions you might have and/or if you want some other model quantized.
68
+
69
+ ## Thanks
70
+
71
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
72
+ me use its servers and providing upgrades to my workstation to enable
73
+ this work in my free time.
74
+
75
+ <!-- end -->