mradermacher commited on
Commit
e9ae5b4
·
verified ·
1 Parent(s): e08bf6e

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/macadeliccc/magistrate-3.2-3b-it
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: macadeliccc/magistrate-3.2-3b-it
3
+ datasets:
4
+ - teknium/OpenHermes-2.5
5
+ - NousResearch/hermes-function-calling-v1
6
+ - arcee-ai/The-Tome
7
+ - cognitivecomputations/SystemChat-2.0
8
+ language:
9
+ - en
10
+ library_name: transformers
11
+ license: llama3.2
12
+ quantized_by: mradermacher
13
+ tags:
14
+ - spectrum
15
+ - llama-3
16
+ - axolotl
17
+ - legal
18
+ - HFforLegal
19
+ ---
20
+ ## About
21
+
22
  <!-- ### quantize_version: 2 -->
23
  <!-- ### output_tensor_quantised: 1 -->
24
  <!-- ### convert_type: hf -->
25
  <!-- ### vocab_type: -->
26
  <!-- ### tags: -->
27
  static quants of https://huggingface.co/macadeliccc/magistrate-3.2-3b-it
28
+
29
+ <!-- provided-files -->
30
+ 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.
31
+ ## Usage
32
+
33
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
34
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
35
+ more details, including on how to concatenate multi-part files.
36
+
37
+ ## Provided Quants
38
+
39
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
40
+
41
+ | Link | Type | Size/GB | Notes |
42
+ |:-----|:-----|--------:|:------|
43
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q2_K.gguf) | Q2_K | 1.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q3_K_L.gguf) | Q3_K_L | 1.9 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q5_K_S.gguf) | Q5_K_S | 2.4 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q5_K_M.gguf) | Q5_K_M | 2.4 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q6_K.gguf) | Q6_K | 2.7 | very good quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/magistrate-3.2-3b-it-GGUF/resolve/main/magistrate-3.2-3b-it.f16.gguf) | f16 | 6.5 | 16 bpw, overkill |
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. 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.
74
+
75
+ <!-- end -->