base_model:
- Infermatic/R1-vortex-70B-L3.3-v1
- huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
library_name: transformers
tags:
- mergekit
- merge
R1-vortex-70B-L3.3-v2
This quant was made for and by Infermatic.ai
Darker version of the v1, this version has Fallen-Llama-3.3-R1-70B-v1 and DeepSeek-R1-Distill-Llama-70B-abliterated merged on the previous V1 model.
Some of the reviews from the testers report:
This model does a great job of neutralizing some of the positivity bias, making interactions feel more balanced and natural. It also incorporates elements of R1, meaning it won’t just passively agree—it can push back and argue when appropriate. Additionally, it handles characters well, maintaining their distinct personalities throughout interactions.
We are searching for more feedback, Join the discord server and jump in the conversation! https://discord.gg/tDh9qpArbf
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 Infermatic/R1-vortex-70B-L3.3-v1 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
name: R1-vortex-70B-L3.3-v2
merge_method: model_stock
base_model: Infermatic/R1-vortex-70B-L3.3-v1
models:
- model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
- model: huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
dtype: bfloat16