Hugging Face's logo

RichardErkhov
/
picAIso_-_TARS-8B-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
111cdcc
•
1 Parent(s): 4166d46

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +99 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ TARS-8B - GGUF
11
+ - Model creator: https://huggingface.co/picAIso/
12
+ - Original model: https://huggingface.co/picAIso/TARS-8B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [TARS-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [TARS-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [TARS-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [TARS-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [TARS-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [TARS-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [TARS-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [TARS-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [TARS-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [TARS-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [TARS-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [TARS-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [TARS-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [TARS-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [TARS-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [TARS-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [TARS-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [TARS-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [TARS-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [TARS-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [TARS-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [TARS-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/picAIso_-_TARS-8B-gguf/blob/main/TARS-8B.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ base_model:
46
+ - NousResearch/Hermes-2-Pro-Llama-3-8B
47
+ - nbeerbower/llama-3-gutenberg-8B
48
+ - MaziyarPanahi/Llama-3-8B-Instruct-v0.9
49
+ library_name: transformers
50
+ tags:
51
+ - mergekit
52
+ - merge
53
+ - merging
54
+ - llama3
55
+ - merged
56
+ license: llama3
57
+ language:
58
+ - en
59
+ ---
60
+ # merge
61
+
62
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
63
+
64
+ ## Merge Details
65
+ ### Merge Method
66
+
67
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [MaziyarPanahi/Llama-3-8B-Instruct-v0.9](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9) as a base.
68
+
69
+ ### Models Merged
70
+
71
+ The following models were included in the merge:
72
+ * [NousResearch/Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)
73
+ * [nbeerbower/llama-3-gutenberg-8B](https://huggingface.co/nbeerbower/llama-3-gutenberg-8B)
74
+
75
+ ### Configuration
76
+
77
+ The following YAML configuration was used to produce this model:
78
+
79
+ ```yaml
80
+ models:
81
+ - model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9
82
+ #no parameters necessary for base model
83
+ - model: NousResearch/Hermes-2-Pro-Llama-3-8B
84
+ parameters:
85
+ density: 0.5
86
+ weight: 0.8
87
+ - model: nbeerbower/llama-3-gutenberg-8B
88
+ parameters:
89
+ density: 0.5
90
+ weight: 0.8
91
+
92
+ merge_method: ties
93
+ base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9
94
+ parameters:
95
+ normalize: false
96
+ int8_mask: true
97
+ dtype: float16
98
+ ```
99
+