mradermacher commited on
Commit
f1d37d8
1 Parent(s): 2141a5d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md CHANGED
@@ -1,6 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct
3
+ datasets:
4
+ - Vikhrmodels/GrandMaster-PRO-MAX
5
+ language:
6
+ - ru
7
+ - en
8
+ library_name: transformers
9
+ license: llama3.2
10
+ model_name: Vikhr-Llama-3.2-1B-instruct
11
+ quantized_by: mradermacher
12
+ ---
13
+ ## About
14
+
15
  <!-- ### quantize_version: 2 -->
16
  <!-- ### output_tensor_quantised: 1 -->
17
  <!-- ### convert_type: hf -->
18
  <!-- ### vocab_type: -->
19
  <!-- ### tags: -->
20
  static quants of https://huggingface.co/Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct
21
+
22
+ <!-- provided-files -->
23
+ 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.
24
+ ## Usage
25
+
26
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
27
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
28
+ more details, including on how to concatenate multi-part files.
29
+
30
+ ## Provided Quants
31
+
32
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
33
+
34
+ | Link | Type | Size/GB | Notes |
35
+ |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q2_K.gguf) | Q2_K | 0.7 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.IQ3_XS.gguf) | IQ3_XS | 0.7 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.IQ3_S.gguf) | IQ3_S | 0.7 | beats Q3_K* |
40
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.IQ3_M.gguf) | IQ3_M | 0.8 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct.f16.gguf) | f16 | 2.6 | 16 bpw, overkill |
51
+
52
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
53
+ types (lower is better):
54
+
55
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
56
+
57
+ And here are Artefact2's thoughts on the matter:
58
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
59
+
60
+ ## FAQ / Model Request
61
+
62
+ See https://huggingface.co/mradermacher/model_requests for some answers to
63
+ questions you might have and/or if you want some other model quantized.
64
+
65
+ ## Thanks
66
+
67
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
68
+ me use its servers and providing upgrades to my workstation to enable
69
+ 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.
70
+
71
+ <!-- end -->