mradermacher commited on
Commit
809b11d
1 Parent(s): a389ce3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -0
README.md CHANGED
@@ -1,6 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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/FPHam/Free_Sydney_V2_Mistral_7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: FPHam/Free_Sydney_V2_Mistral_7b
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ tags:
8
+ - llm
9
+ - llama
10
+ - llama2
11
+ ---
12
+ ## About
13
+
14
  <!-- ### quantize_version: 2 -->
15
  <!-- ### output_tensor_quantised: 1 -->
16
  <!-- ### convert_type: hf -->
17
  <!-- ### vocab_type: -->
18
  <!-- ### tags: -->
19
  static quants of https://huggingface.co/FPHam/Free_Sydney_V2_Mistral_7b
20
+
21
+ <!-- provided-files -->
22
+ 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.
23
+ ## Usage
24
+
25
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
26
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
27
+ more details, including on how to concatenate multi-part files.
28
+
29
+ ## Provided Quants
30
+
31
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
32
+
33
+ | Link | Type | Size/GB | Notes |
34
+ |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q2_K.gguf) | Q2_K | 2.8 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
39
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.IQ3_M.gguf) | IQ3_M | 3.4 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Free_Sydney_V2_Mistral_7b-GGUF/resolve/main/Free_Sydney_V2_Mistral_7b.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
50
+
51
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
52
+ types (lower is better):
53
+
54
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
55
+
56
+ And here are Artefact2's thoughts on the matter:
57
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
58
+
59
+ ## FAQ / Model Request
60
+
61
+ See https://huggingface.co/mradermacher/model_requests for some answers to
62
+ questions you might have and/or if you want some other model quantized.
63
+
64
+ ## Thanks
65
+
66
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
67
+ me use its servers and providing upgrades to my workstation to enable
68
+ this work in my free time.
69
+
70
+ <!-- end -->