Hugging Face's logo

RichardErkhov
/
bunnycore_-_Maverick-8B-gguf

GGUF
conversational
Model card Files
xet
 Community
RichardErkhov commited on
Commit
7bf9a30
·
verified ·
1 Parent(s): dd55b3e

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +68 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Maverick-8B - GGUF
11
+ - Model creator: https://huggingface.co/bunnycore/
12
+ - Original model: https://huggingface.co/bunnycore/Maverick-8B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Maverick-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [Maverick-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [Maverick-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [Maverick-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [Maverick-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [Maverick-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [Maverick-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [Maverick-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [Maverick-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [Maverick-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [Maverick-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [Maverick-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [Maverick-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [Maverick-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [Maverick-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [Maverick-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [Maverick-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [Maverick-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [Maverick-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [Maverick-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [Maverick-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [Maverick-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_Maverick-8B-gguf/blob/main/Maverick-8B.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: llama3
46
+ tags:
47
+ - merge
48
+ - mergekit
49
+ - lazymergekit
50
+ ---
51
+
52
+ # Maverick-8B
53
+
54
+ Maverick-8B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
55
+
56
+ ## 🧩 Configuration
57
+
58
+ ```yaml
59
+ models:
60
+ - model: bunnycore/Cognitron-8B
61
+ - model: failspy/Llama-3-8B-Instruct-abliterated
62
+ - model: TIGER-Lab/MAmmoTH2-8B-Plus
63
+ merge_method: model_stock
64
+ base_model: bunnycore/Cognitron-8B
65
+ dtype: bfloat16
66
+
67
+ ```
68
+