RichardErkhov commited on
Commit
9406728
1 Parent(s): d3aeae7

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Hermes-2-Theta-L3-Euryale-Ties-0.8-70B - GGUF
11
+ - Model creator: https://huggingface.co/juvi21/
12
+ - Original model: https://huggingface.co/juvi21/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q2_K.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q2_K.gguf) | Q2_K | 24.56GB |
18
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_XS.gguf) | IQ3_XS | 27.29GB |
19
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_S.gguf) | IQ3_S | 28.79GB |
20
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_S.gguf) | Q3_K_S | 28.79GB |
21
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_M.gguf) | IQ3_M | 29.74GB |
22
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K.gguf) | Q3_K | 31.91GB |
23
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_M.gguf) | Q3_K_M | 31.91GB |
24
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_L.gguf) | Q3_K_L | 34.59GB |
25
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ4_XS.gguf) | IQ4_XS | 35.64GB |
26
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_0.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/blob/main/Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_0.gguf) | Q4_0 | 37.22GB |
27
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | IQ4_NL | 37.58GB |
28
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q4_K_S | 37.58GB |
29
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_K.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q4_K | 39.6GB |
30
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q4_K_M | 39.6GB |
31
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_1.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q4_1 | 41.27GB |
32
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_0.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q5_0 | 45.32GB |
33
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q5_K_S | 45.32GB |
34
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_K.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q5_K | 46.52GB |
35
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q5_K_M | 46.52GB |
36
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_1.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q5_1 | 49.36GB |
37
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q6_K.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q6_K | 53.91GB |
38
+ | [Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q8_0.gguf](https://huggingface.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf/tree/main/) | Q8_0 | 69.83GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ base_model:
46
+ - Sao10K/L3-70B-Euryale-v2.1
47
+ - NousResearch/Hermes-2-Theta-Llama-3-70B
48
+ library_name: transformers
49
+ tags:
50
+ - mergekit
51
+ - merge
52
+
53
+ ---
54
+ # Hermes-2-Theta-L3-Euryale-Ties-0.8-70B
55
+
56
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
57
+ I wanted to have enhanced roleplay performance and merged two of my favorite models together. I maybe release some merges like this with different methods and biases. This config seemed to be the best mix of both world on first glance.
58
+ I will update my experiences further in the future.
59
+
60
+ ## Merge Details
61
+ ### Merge Method
62
+
63
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Hermes-2-Theta-Llama-3-70B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B) as a base.
64
+
65
+ ### Models Merged
66
+
67
+ The following models were included in the merge:
68
+ * [Sao10K/L3-70B-Euryale-v2.1](https://huggingface.co/Sao10K/L3-70B-Euryale-v2.1)
69
+
70
+ ### Configuration
71
+
72
+ The following YAML configuration was used to produce this model:
73
+
74
+ ```yaml
75
+ models:
76
+ - model: NousResearch/Hermes-2-Theta-Llama-3-70B
77
+ parameters:
78
+ weight: 0.8
79
+ - model: Sao10K/L3-70B-Euryale-v2.1
80
+ parameters:
81
+ weight: 0.2
82
+ merge_method: ties
83
+ base_model: NousResearch/Hermes-2-Theta-Llama-3-70B
84
+ parameters:
85
+ density: 0.7
86
+ normalize: true
87
+ dtype: float16
88
+ tokenizer_source: base
89
+
90
+ ```
91
+
92
+