Hugging Face's logo

RichardErkhov
/
bunnycore_-_Gemma2-9b-Max-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
196a787
·
verified ·
1 Parent(s): 89589a0

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Gemma2-9b-Max - GGUF
11
+ - Model creator: https://huggingface.co/bunnycore/
12
+ - Original model: https://huggingface.co/bunnycore/Gemma2-9b-Max/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Gemma2-9b-Max.Q2_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q2_K.gguf) | Q2_K | 3.54GB |
18
+ | [Gemma2-9b-Max.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.IQ3_XS.gguf) | IQ3_XS | 3.86GB |
19
+ | [Gemma2-9b-Max.IQ3_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.IQ3_S.gguf) | IQ3_S | 4.04GB |
20
+ | [Gemma2-9b-Max.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q3_K_S.gguf) | Q3_K_S | 4.04GB |
21
+ | [Gemma2-9b-Max.IQ3_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.IQ3_M.gguf) | IQ3_M | 4.19GB |
22
+ | [Gemma2-9b-Max.Q3_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q3_K.gguf) | Q3_K | 4.43GB |
23
+ | [Gemma2-9b-Max.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q3_K_M.gguf) | Q3_K_M | 4.43GB |
24
+ | [Gemma2-9b-Max.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q3_K_L.gguf) | Q3_K_L | 4.78GB |
25
+ | [Gemma2-9b-Max.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.IQ4_XS.gguf) | IQ4_XS | 4.86GB |
26
+ | [Gemma2-9b-Max.Q4_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q4_0.gguf) | Q4_0 | 5.07GB |
27
+ | [Gemma2-9b-Max.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.IQ4_NL.gguf) | IQ4_NL | 5.1GB |
28
+ | [Gemma2-9b-Max.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q4_K_S.gguf) | Q4_K_S | 5.1GB |
29
+ | [Gemma2-9b-Max.Q4_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q4_K.gguf) | Q4_K | 5.37GB |
30
+ | [Gemma2-9b-Max.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q4_K_M.gguf) | Q4_K_M | 5.37GB |
31
+ | [Gemma2-9b-Max.Q4_1.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q4_1.gguf) | Q4_1 | 5.55GB |
32
+ | [Gemma2-9b-Max.Q5_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q5_0.gguf) | Q5_0 | 6.04GB |
33
+ | [Gemma2-9b-Max.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q5_K_S.gguf) | Q5_K_S | 6.04GB |
34
+ | [Gemma2-9b-Max.Q5_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q5_K.gguf) | Q5_K | 6.19GB |
35
+ | [Gemma2-9b-Max.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q5_K_M.gguf) | Q5_K_M | 6.19GB |
36
+ | [Gemma2-9b-Max.Q5_1.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q5_1.gguf) | Q5_1 | 6.52GB |
37
+ | [Gemma2-9b-Max.Q6_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q6_K.gguf) | Q6_K | 7.07GB |
38
+ | [Gemma2-9b-Max.Q8_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Gemma2-9b-Max-gguf/blob/main/Gemma2-9b-Max.Q8_0.gguf) | Q8_0 | 9.15GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ base_model:
46
+ - ehristoforu/Gemma2-9B-it-psy10k-mental_health
47
+ - bunnycore/HyperGemma-2-9B
48
+ - crestf411/gemma2-9B-sunfall-v0.5.2
49
+ - bunnycore/Gemma2-9b-Uncensored-Lora
50
+ - IlyaGusev/gemma-2-9b-it-abliterated
51
+ library_name: transformers
52
+ tags:
53
+ - mergekit
54
+ - merge
55
+
56
+ ---
57
+ # merge
58
+
59
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
60
+
61
+ ## Merge Details
62
+ ### Merge Method
63
+
64
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [bunnycore/HyperGemma-2-9B](https://huggingface.co/bunnycore/HyperGemma-2-9B) as a base.
65
+
66
+ ### Models Merged
67
+
68
+ The following models were included in the merge:
69
+ * [ehristoforu/Gemma2-9B-it-psy10k-mental_health](https://huggingface.co/ehristoforu/Gemma2-9B-it-psy10k-mental_health)
70
+ * [crestf411/gemma2-9B-sunfall-v0.5.2](https://huggingface.co/crestf411/gemma2-9B-sunfall-v0.5.2) + [bunnycore/Gemma2-9b-Uncensored-Lora](https://huggingface.co/bunnycore/Gemma2-9b-Uncensored-Lora)
71
+ * [IlyaGusev/gemma-2-9b-it-abliterated](https://huggingface.co/IlyaGusev/gemma-2-9b-it-abliterated)
72
+
73
+ ### Configuration
74
+
75
+ The following YAML configuration was used to produce this model:
76
+
77
+ ```yaml
78
+
79
+ models:
80
+ - model: bunnycore/HyperGemma-2-9B
81
+ - model: crestf411/gemma2-9B-sunfall-v0.5.2+bunnycore/Gemma2-9b-Uncensored-Lora
82
+ - model: IlyaGusev/gemma-2-9b-it-abliterated
83
+ - model: ehristoforu/Gemma2-9B-it-psy10k-mental_health
84
+ merge_method: model_stock
85
+ base_model: bunnycore/HyperGemma-2-9B
86
+ dtype: bfloat16
87
+
88
+
89
+ ```
90
+
91
+