about
Original name : Llama_3.x_70b_Dolnemhertulimtess_v1.0
Also known as : Llama_3.x_70b_Dolmen_v1.0 (1.1 will come soon)
This model is essentially a Llama 3.1 smart brick based on by a 3.0->3.3 "port", to be used in second level merges.
This time, for the base, I used a Llama 3.0 Dolphin 2.9.1/Llama 3.3 instruct abliterated merge, in order to get both the capabilities of each model, and notably Dolphin, not ported on Llama 70b 3.1 or 3.3 by CognitiveComputations.
Then, I added the best 'instructions oriented' finetunes I know, simple as that.
The model is highly uncensored, quite intelligent, and can be used as a standalone.
merge
This is a merge of pre-trained language models created using
mergekit.
Merge Details
Merge Method
This model was merged using the
Model Stock merge method using
Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
1merge_method: model_stock
2models:
3 - model: Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
4 parameters:
5 weight: 1.0
6 - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
7 parameters:
8 weight: 1.0
9 - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
10 parameters:
11 weight: 1.0
12 - model: huihui-ai/Llama-3.1-Tulu-3-70B-abliterated
13 parameters:
14 weight: 1.0
15 - model: huihui-ai/Tess-R1-Limerick-Llama-3.1-70B-abliterated
16 parameters:
17 weight: 1.0
18 - model: migtissera/Tess-3-Llama-3.1-70B
19 parameters:
20 weight: 1.0
21base_model: Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
22dtype: bfloat16
23out_dtype: bfloat16
24parameters:
25 int8_mask: true
26 normalize: true
27 rescale: false
28 filter_wise: false
29 smooth: false
30 allow_negative_weights: false
31chat_template: auto
32tokenizer:
33 source: union
