Hugging Face's logo

mradermacher
/
Mahou-1.2a-mistral-7B-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
66fe753
•
1 Parent(s): 5b39857

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +71 -0
README.md CHANGED
@@ -1,5 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  weighted/imatrix quants of https://huggingface.co/flammenai/Mahou-1.2a-mistral-7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: flammenai/Mahou-1.2a-mistral-7B
3
+ datasets:
4
+ - flammenai/FlameMix-DPO-v1
5
+ - flammenai/Grill-preprod-v1_chatML
6
+ - flammenai/Grill-preprod-v2_chatML
7
+ language:
8
+ - en
9
+ library_name: transformers
10
+ license: apache-2.0
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
  weighted/imatrix quants of https://huggingface.co/flammenai/Mahou-1.2a-mistral-7B
20
+
21
+ <!-- provided-files -->
22
+ static quants are available at https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-GGUF
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/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.2a-mistral-7B-i1-GGUF/resolve/main/Mahou-1.2a-mistral-7B.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
56
+
57
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
58
+ types (lower is better):
59
+
60
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
61
+
62
+ And here are Artefact2's thoughts on the matter:
63
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
64
+
65
+ ## FAQ / Model Request
66
+
67
+ See https://huggingface.co/mradermacher/model_requests for some answers to
68
+ questions you might have and/or if you want some other model quantized.
69
+
70
+ ## Thanks
71
+
72
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
73
+ me use its servers and providing upgrades to my workstation to enable
74
+ this work in my free time.
75
+
76
+ <!-- end -->