Hugging Face's logo

RichardErkhov
/
djuna_-_MN-Chinofun-12B-2-gguf

GGUF
Model card Files Community
RichardErkhov commited on
Commit
c9284f3
·
verified ·
1 Parent(s): d1ea67e

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ MN-Chinofun-12B-2 - GGUF
11
+ - Model creator: https://huggingface.co/djuna/
12
+ - Original model: https://huggingface.co/djuna/MN-Chinofun-12B-2/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [MN-Chinofun-12B-2.Q2_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q2_K.gguf) | Q2_K | 4.46GB |
18
+ | [MN-Chinofun-12B-2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q3_K_S.gguf) | Q3_K_S | 5.15GB |
19
+ | [MN-Chinofun-12B-2.Q3_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q3_K.gguf) | Q3_K | 5.67GB |
20
+ | [MN-Chinofun-12B-2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q3_K_M.gguf) | Q3_K_M | 5.67GB |
21
+ | [MN-Chinofun-12B-2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q3_K_L.gguf) | Q3_K_L | 6.11GB |
22
+ | [MN-Chinofun-12B-2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.IQ4_XS.gguf) | IQ4_XS | 6.33GB |
23
+ | [MN-Chinofun-12B-2.Q4_0.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q4_0.gguf) | Q4_0 | 6.59GB |
24
+ | [MN-Chinofun-12B-2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.IQ4_NL.gguf) | IQ4_NL | 6.65GB |
25
+ | [MN-Chinofun-12B-2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q4_K_S.gguf) | Q4_K_S | 6.63GB |
26
+ | [MN-Chinofun-12B-2.Q4_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q4_K.gguf) | Q4_K | 6.96GB |
27
+ | [MN-Chinofun-12B-2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q4_K_M.gguf) | Q4_K_M | 6.96GB |
28
+ | [MN-Chinofun-12B-2.Q4_1.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q4_1.gguf) | Q4_1 | 7.26GB |
29
+ | [MN-Chinofun-12B-2.Q5_0.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q5_0.gguf) | Q5_0 | 7.93GB |
30
+ | [MN-Chinofun-12B-2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q5_K_S.gguf) | Q5_K_S | 7.93GB |
31
+ | [MN-Chinofun-12B-2.Q5_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q5_K.gguf) | Q5_K | 8.13GB |
32
+ | [MN-Chinofun-12B-2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q5_K_M.gguf) | Q5_K_M | 8.13GB |
33
+ | [MN-Chinofun-12B-2.Q5_1.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q5_1.gguf) | Q5_1 | 8.61GB |
34
+ | [MN-Chinofun-12B-2.Q6_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q6_K.gguf) | Q6_K | 9.37GB |
35
+ | [MN-Chinofun-12B-2.Q8_0.gguf](https://huggingface.co/RichardErkhov/djuna_-_MN-Chinofun-12B-2-gguf/blob/main/MN-Chinofun-12B-2.Q8_0.gguf) | Q8_0 | 12.13GB |
36
+
37
+
38
+
39
+
40
+ Original model description:
41
+ ---
42
+ base_model:
43
+ - grimjim/magnum-consolidatum-v1-12b
44
+ - spow12/ChatWaifu_v1.4
45
+ - GalrionSoftworks/Canidori-12B-v1
46
+ - Nohobby/MN-12B-Siskin-v0.2
47
+ - ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
48
+ - RozGrov/NemoDori-v0.2.2-12B-MN-ties
49
+ library_name: transformers
50
+ tags:
51
+ - mergekit
52
+ - merge
53
+
54
+ ---
55
+ # merge
56
+
57
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
58
+
59
+ ## Merge Details
60
+ ### Merge Method
61
+
62
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2](https://huggingface.co/ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2) as a base.
63
+
64
+ ### Models Merged
65
+
66
+ The following models were included in the merge:
67
+ * [grimjim/magnum-consolidatum-v1-12b](https://huggingface.co/grimjim/magnum-consolidatum-v1-12b)
68
+ * [spow12/ChatWaifu_v1.4](https://huggingface.co/spow12/ChatWaifu_v1.4)
69
+ * [GalrionSoftworks/Canidori-12B-v1](https://huggingface.co/GalrionSoftworks/Canidori-12B-v1)
70
+ * [Nohobby/MN-12B-Siskin-v0.2](https://huggingface.co/Nohobby/MN-12B-Siskin-v0.2)
71
+ * [RozGrov/NemoDori-v0.2.2-12B-MN-ties](https://huggingface.co/RozGrov/NemoDori-v0.2.2-12B-MN-ties)
72
+
73
+ ### Configuration
74
+
75
+ The following YAML configuration was used to produce this model:
76
+
77
+ ```yaml
78
+ models:
79
+ - model: Nohobby/MN-12B-Siskin-v0.2
80
+ - model: spow12/ChatWaifu_v1.4
81
+ - model: grimjim/magnum-consolidatum-v1-12b
82
+ - model: RozGrov/NemoDori-v0.2.2-12B-MN-ties
83
+ - model: GalrionSoftworks/Canidori-12B-v1
84
+ merge_method: model_stock
85
+ base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
86
+ dtype: bfloat16
87
+ ```
88
+
89
+