Hugging Face's logo

RichardErkhov
/
bunnycore_-_LLama-3.1-4B-TitanFusion-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
8bb6c49
•
1 Parent(s): edb2bbc

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ LLama-3.1-4B-TitanFusion - GGUF
11
+ - Model creator: https://huggingface.co/bunnycore/
12
+ - Original model: https://huggingface.co/bunnycore/LLama-3.1-4B-TitanFusion/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [LLama-3.1-4B-TitanFusion.Q2_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q2_K.gguf) | Q2_K | 1.71GB |
18
+ | [LLama-3.1-4B-TitanFusion.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q3_K_S.gguf) | Q3_K_S | 1.96GB |
19
+ | [LLama-3.1-4B-TitanFusion.Q3_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q3_K.gguf) | Q3_K | 2.14GB |
20
+ | [LLama-3.1-4B-TitanFusion.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q3_K_M.gguf) | Q3_K_M | 2.14GB |
21
+ | [LLama-3.1-4B-TitanFusion.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q3_K_L.gguf) | Q3_K_L | 2.3GB |
22
+ | [LLama-3.1-4B-TitanFusion.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.IQ4_XS.gguf) | IQ4_XS | 2.38GB |
23
+ | [LLama-3.1-4B-TitanFusion.Q4_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q4_0.gguf) | Q4_0 | 1.97GB |
24
+ | [LLama-3.1-4B-TitanFusion.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.IQ4_NL.gguf) | IQ4_NL | 2.49GB |
25
+ | [LLama-3.1-4B-TitanFusion.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q4_K_S.gguf) | Q4_K_S | 2.48GB |
26
+ | [LLama-3.1-4B-TitanFusion.Q4_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q4_K.gguf) | Q4_K | 2.59GB |
27
+ | [LLama-3.1-4B-TitanFusion.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q4_K_M.gguf) | Q4_K_M | 2.19GB |
28
+ | [LLama-3.1-4B-TitanFusion.Q4_1.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q4_1.gguf) | Q4_1 | 2.71GB |
29
+ | [LLama-3.1-4B-TitanFusion.Q5_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q5_0.gguf) | Q5_0 | 2.95GB |
30
+ | [LLama-3.1-4B-TitanFusion.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q5_K_S.gguf) | Q5_K_S | 2.95GB |
31
+ | [LLama-3.1-4B-TitanFusion.Q5_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q5_K.gguf) | Q5_K | 3.01GB |
32
+ | [LLama-3.1-4B-TitanFusion.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q5_K_M.gguf) | Q5_K_M | 2.33GB |
33
+ | [LLama-3.1-4B-TitanFusion.Q5_1.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q5_1.gguf) | Q5_1 | 3.19GB |
34
+ | [LLama-3.1-4B-TitanFusion.Q6_K.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q6_K.gguf) | Q6_K | 1.93GB |
35
+ | [LLama-3.1-4B-TitanFusion.Q8_0.gguf](https://huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-4B-TitanFusion-gguf/blob/main/LLama-3.1-4B-TitanFusion.Q8_0.gguf) | Q8_0 | 4.47GB |
36
+
37
+
38
+
39
+
40
+ Original model description:
41
+ ---
42
+ base_model:
43
+ - Magpie-Align/MagpieLM-4B-Chat-v0.1
44
+ - anthracite-org/magnum-v2-4b
45
+ - TheDrummer/Hubble-4B-v1
46
+ library_name: transformers
47
+ tags:
48
+ - mergekit
49
+ - merge
50
+
51
+ ---
52
+ # merge
53
+
54
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
55
+
56
+ ## Merge Details
57
+ ### Merge Method
58
+
59
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Magpie-Align/MagpieLM-4B-Chat-v0.1](https://huggingface.co/Magpie-Align/MagpieLM-4B-Chat-v0.1) as a base.
60
+
61
+ ### Models Merged
62
+
63
+ The following models were included in the merge:
64
+ * [anthracite-org/magnum-v2-4b](https://huggingface.co/anthracite-org/magnum-v2-4b)
65
+ * [TheDrummer/Hubble-4B-v1](https://huggingface.co/TheDrummer/Hubble-4B-v1)
66
+
67
+ ### Configuration
68
+
69
+ The following YAML configuration was used to produce this model:
70
+
71
+ ```yaml
72
+ models:
73
+ - model: Magpie-Align/MagpieLM-4B-Chat-v0.1
74
+ - model: anthracite-org/magnum-v2-4b
75
+ - model: TheDrummer/Hubble-4B-v1
76
+ merge_method: model_stock
77
+ base_model: Magpie-Align/MagpieLM-4B-Chat-v0.1
78
+ dtype: bfloat16
79
+
80
+ ```
81
+
82
+