mradermacher commited on
Commit
a86690a
1 Parent(s): b3912fd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +66 -0
README.md CHANGED
@@ -1,6 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/mrcuddle/Tiny-DarkLlama-Chat
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mrcuddle/Tiny-DarkLlama-Chat
3
+ datasets:
4
+ - ChaoticNeutrals/Synthetic-Dark-RP
5
+ - ChaoticNeutrals/Synthetic-RP
6
+ - ChaoticNeutrals/Luminous_Opus
7
+ - NobodyExistsOnTheInternet/ToxicQAFinal
8
+ language:
9
+ - en
10
+ library_name: transformers
11
+ license: other
12
+ quantized_by: mradermacher
13
+ tags:
14
+ - autotrain
15
+ - text-generation-inference
16
+ - text-generation
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/mrcuddle/Tiny-DarkLlama-Chat
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/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q2_K.gguf) | Q2_K | 0.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q3_K_S.gguf) | Q3_K_S | 0.6 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q3_K_L.gguf) | Q3_K_L | 0.7 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q5_K_S.gguf) | Q5_K_S | 0.9 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q5_K_M.gguf) | Q5_K_M | 0.9 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q6_K.gguf) | Q6_K | 1.0 | very good quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Tiny-DarkLlama-Chat-GGUF/resolve/main/Tiny-DarkLlama-Chat.f16.gguf) | f16 | 2.3 | 16 bpw, overkill |
52
+
53
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
54
+ types (lower is better):
55
+
56
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
57
+
58
+ And here are Artefact2's thoughts on the matter:
59
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
60
+
61
+ ## FAQ / Model Request
62
+
63
+ See https://huggingface.co/mradermacher/model_requests for some answers to
64
+ questions you might have and/or if you want some other model quantized.
65
+
66
+ ## Thanks
67
+
68
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
69
+ me use its servers and providing upgrades to my workstation to enable
70
+ this work in my free time.
71
+
72
+ <!-- end -->