Hugging Face's logo

RichardErkhov
/
Bacon666_-_Phenom-12B-0.1-gguf

GGUF
Model card Files
xet
Community
RichardErkhov commited on
Commit
0574387
·
verified ·
1 Parent(s): f32e573

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Phenom-12B-0.1 - GGUF
11
+ - Model creator: https://huggingface.co/Bacon666/
12
+ - Original model: https://huggingface.co/Bacon666/Phenom-12B-0.1/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Phenom-12B-0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q2_K.gguf) | Q2_K | 4.46GB |
18
+ | [Phenom-12B-0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q3_K_S.gguf) | Q3_K_S | 5.15GB |
19
+ | [Phenom-12B-0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q3_K.gguf) | Q3_K | 5.67GB |
20
+ | [Phenom-12B-0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q3_K_M.gguf) | Q3_K_M | 5.67GB |
21
+ | [Phenom-12B-0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q3_K_L.gguf) | Q3_K_L | 6.11GB |
22
+ | [Phenom-12B-0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.IQ4_XS.gguf) | IQ4_XS | 6.33GB |
23
+ | [Phenom-12B-0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q4_0.gguf) | Q4_0 | 6.59GB |
24
+ | [Phenom-12B-0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.IQ4_NL.gguf) | IQ4_NL | 6.65GB |
25
+ | [Phenom-12B-0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q4_K_S.gguf) | Q4_K_S | 6.63GB |
26
+ | [Phenom-12B-0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q4_K.gguf) | Q4_K | 6.96GB |
27
+ | [Phenom-12B-0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q4_K_M.gguf) | Q4_K_M | 6.96GB |
28
+ | [Phenom-12B-0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q4_1.gguf) | Q4_1 | 7.26GB |
29
+ | [Phenom-12B-0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q5_0.gguf) | Q5_0 | 7.93GB |
30
+ | [Phenom-12B-0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q5_K_S.gguf) | Q5_K_S | 7.93GB |
31
+ | [Phenom-12B-0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q5_K.gguf) | Q5_K | 8.13GB |
32
+ | [Phenom-12B-0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q5_K_M.gguf) | Q5_K_M | 8.13GB |
33
+ | [Phenom-12B-0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q5_1.gguf) | Q5_1 | 8.61GB |
34
+ | [Phenom-12B-0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q6_K.gguf) | Q6_K | 9.37GB |
35
+ | [Phenom-12B-0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Bacon666_-_Phenom-12B-0.1-gguf/blob/main/Phenom-12B-0.1.Q8_0.gguf) | Q8_0 | 12.13GB |
36
+
37
+
38
+
39
+
40
+ Original model description:
41
+ ---
42
+ base_model:
43
+ - anthracite-org/magnum-v2.5-12b-kto
44
+ - TheDrummer/Rocinante-12B-v1.1
45
+ - MarinaraSpaghetti/NemoMix-Unleashed-12B
46
+ - elinas/Chronos-Gold-12B-1.0
47
+ library_name: transformers
48
+ tags:
49
+ - mergekit
50
+ - merge
51
+
52
+ ---
53
+ # merge
54
+
55
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
56
+
57
+ ## Merge Details
58
+ ### Merge Method
59
+
60
+ This model was merged using the della_linear merge method using [TheDrummer/Rocinante-12B-v1.1](https://huggingface.co/TheDrummer/Rocinante-12B-v1.1) as a base.
61
+
62
+ ### Models Merged
63
+
64
+ The following models were included in the merge:
65
+ * [anthracite-org/magnum-v2.5-12b-kto](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto)
66
+ * [MarinaraSpaghetti/NemoMix-Unleashed-12B](https://huggingface.co/MarinaraSpaghetti/NemoMix-Unleashed-12B)
67
+ * [elinas/Chronos-Gold-12B-1.0](https://huggingface.co/elinas/Chronos-Gold-12B-1.0)
68
+
69
+ ### Configuration
70
+
71
+ The following YAML configuration was used to produce this model:
72
+
73
+ ```yaml
74
+ models:
75
+ - model: MarinaraSpaghetti/NemoMix-Unleashed-12B
76
+ parameters:
77
+ weight: 0.25
78
+ density: 0.84
79
+ - model: elinas/Chronos-Gold-12B-1.0
80
+ parameters:
81
+ weight: 0.4
82
+ density: 0.88
83
+ - model: anthracite-org/magnum-v2.5-12b-kto
84
+ parameters:
85
+ weight: 0.6
86
+ density: 0.9
87
+ merge_method: della_linear
88
+ base_model: TheDrummer/Rocinante-12B-v1.1
89
+ parameters:
90
+ int8_mask: true
91
+ epsilon: 0.07
92
+ lambda: 1
93
+ dtype: bfloat16
94
+ ```
95
+
96
+