Downloads · 30 days
11
6% of all-time downloads
kainatq/KaidenRp2400_12b_v1
KaidenRp2400_12b_v1 is a text generation model from kainatq. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Merged using mergekit. we first merge some models in merge1 then we megre another list of models in merge2 then we merged them together.
Downloads · 30 days
11
6% of all-time downloads
All-time downloads
188
Public
Parameters
12.2B
24.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors24.5 GB · 100%
From the Hugging Face model README
Merged using mergekit. we first merge some models in merge1 then we megre another list of models in merge2 then we merged them together.
here are intermediate merges: (kainatq/KaidenRp2400_12b_v1_m1](https://huggingface.co/kainatq/KaidenRp2400_12b_v1_m1) https://huggingface.co/kainatq/KaidenRp2400_12b_v1_m2
follow mistral-nemo-base-2407 (chatml) instructions.
merge_method: dare_ties
base_model: mistralai/Mistral-Nemo-Base-2407
tokenizer_source: union
parameters:
density: 0.5
weight: 1.0
models:
- model: Gryphe/Pantheon-RP-1.5-12b-Nemo
parameters:
weight: 0.33
- model: kainatq/RP-king-12b-II
parameters:
weight: 0.33
- model: elinas/Chronos-Gold-12B-1.0
parameters:
weight: 0.34
merge_method: dare_ties
base_model: mistralai/Mistral-Nemo-Base-2407
tokenizer_source: union
parameters:
density: 0.5
weight: 1.0
models:
- model: mergekit-community/MN-Sappho-g2-12B
parameters:
weight: 0.33
- model: nbeerbower/Nemoties-ChatML-12B
parameters:
weight: 0.33
- model: pbevan11/Mistral-Nemo-Baseline-SFT
parameters:
weight: 0.34
merge_method: dare_ties
base_model: mistralai/Mistral-Nemo-Base-2407
tokenizer_source: union
parameters:
density: 0.5
weight: 1.0
models:
- model: kainatq/KaidenRp2400_12b_v1_m1
parameters:
weight: 0.40
- model: kainatq/KaidenRp2400_12b_v1_m2
parameters:
weight: 0.40
- model: mergekit-community/MN-Sappho-j-12B
parameters:
weight: 0.20