Hugging Face's logo

RichardErkhov
/
Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
17813fe
•
1 Parent(s): 4308949

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
+ Hematoma-Gemma-Model-Stock-9B - GGUF
11
+ - Model creator: https://huggingface.co/Nekuromento/
12
+ - Original model: https://huggingface.co/Nekuromento/Hematoma-Gemma-Model-Stock-9B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Hematoma-Gemma-Model-Stock-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q2_K.gguf) | Q2_K | 3.54GB |
18
+ | [Hematoma-Gemma-Model-Stock-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.IQ3_XS.gguf) | IQ3_XS | 3.86GB |
19
+ | [Hematoma-Gemma-Model-Stock-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.IQ3_S.gguf) | IQ3_S | 4.04GB |
20
+ | [Hematoma-Gemma-Model-Stock-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q3_K_S.gguf) | Q3_K_S | 4.04GB |
21
+ | [Hematoma-Gemma-Model-Stock-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.IQ3_M.gguf) | IQ3_M | 4.19GB |
22
+ | [Hematoma-Gemma-Model-Stock-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q3_K.gguf) | Q3_K | 4.43GB |
23
+ | [Hematoma-Gemma-Model-Stock-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q3_K_M.gguf) | Q3_K_M | 4.43GB |
24
+ | [Hematoma-Gemma-Model-Stock-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q3_K_L.gguf) | Q3_K_L | 4.78GB |
25
+ | [Hematoma-Gemma-Model-Stock-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.IQ4_XS.gguf) | IQ4_XS | 4.86GB |
26
+ | [Hematoma-Gemma-Model-Stock-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q4_0.gguf) | Q4_0 | 5.07GB |
27
+ | [Hematoma-Gemma-Model-Stock-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.IQ4_NL.gguf) | IQ4_NL | 5.1GB |
28
+ | [Hematoma-Gemma-Model-Stock-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q4_K_S.gguf) | Q4_K_S | 5.1GB |
29
+ | [Hematoma-Gemma-Model-Stock-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q4_K.gguf) | Q4_K | 5.37GB |
30
+ | [Hematoma-Gemma-Model-Stock-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q4_K_M.gguf) | Q4_K_M | 5.37GB |
31
+ | [Hematoma-Gemma-Model-Stock-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q4_1.gguf) | Q4_1 | 5.55GB |
32
+ | [Hematoma-Gemma-Model-Stock-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q5_0.gguf) | Q5_0 | 6.04GB |
33
+ | [Hematoma-Gemma-Model-Stock-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q5_K_S.gguf) | Q5_K_S | 6.04GB |
34
+ | [Hematoma-Gemma-Model-Stock-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q5_K.gguf) | Q5_K | 6.19GB |
35
+ | [Hematoma-Gemma-Model-Stock-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q5_K_M.gguf) | Q5_K_M | 6.19GB |
36
+ | [Hematoma-Gemma-Model-Stock-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q5_1.gguf) | Q5_1 | 6.52GB |
37
+ | [Hematoma-Gemma-Model-Stock-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q6_K.gguf) | Q6_K | 7.07GB |
38
+ | [Hematoma-Gemma-Model-Stock-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Nekuromento_-_Hematoma-Gemma-Model-Stock-9B-gguf/blob/main/Hematoma-Gemma-Model-Stock-9B.Q8_0.gguf) | Q8_0 | 9.15GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ base_model:
46
+ - UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
47
+ - BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
48
+ - princeton-nlp/gemma-2-9b-it-SimPO
49
+ - wzhouad/gemma-2-9b-it-WPO-HB
50
+ library_name: transformers
51
+ tags:
52
+ - mergekit
53
+ - merge
54
+
55
+ ---
56
+ # merge
57
+
58
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
59
+
60
+ ## Merge Details
61
+ ### Merge Method
62
+
63
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3) as a base.
64
+
65
+ ### Models Merged
66
+
67
+ The following models were included in the merge:
68
+ * [BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference](https://huggingface.co/BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference)
69
+ * [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO)
70
+ * [wzhouad/gemma-2-9b-it-WPO-HB](https://huggingface.co/wzhouad/gemma-2-9b-it-WPO-HB)
71
+
72
+ ### Configuration
73
+
74
+ The following YAML configuration was used to produce this model:
75
+
76
+ ```yaml
77
+ models:
78
+ - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
79
+ - model: BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
80
+ - model: princeton-nlp/gemma-2-9b-it-SimPO
81
+ - model: wzhouad/gemma-2-9b-it-WPO-HB
82
+ merge_method: model_stock
83
+ base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
84
+ normalize: false
85
+ int8_mask: true
86
+ dtype: float16
87
+ ```
88
+
89
+