This is the un-quantized fp16 version for training and merging. If you want the quantized version for inference please refer to the repo bellow:
This model is a TIES merger of Mixtral-8x7B-Instruct-v0.1 and bagel-dpo-8x7b-v0.2 with MixtralOrochi8x7B being the Base model.
I was very impressed with MixtralOrochi8x7B performance and multifaceted usecases as it is already a merger of many usefull Mixtral models such as Mixtral instruct,
Noromaid-v0.1-mixtral, openbuddy-mixtral and possibly other models that were not named. My goal was to expand the models capabilities and make it even more useful of a model, maybe even competitive with closed source models like Gpt-4. But for that more testing is required. I hope the community can help me determine if its deserving of its name. 😊
This is the second iteration of this model, using better models in the merger to improve performance (hopefully).
1models:
2 - model: Mixtral-8x7B-Instruct-v0.1
3
4 parameters:
5 density: .5
6 weight: 1
7 - model: bagel-dpo-8x7b-v0.2
8 parameters:
9 density: .5
10 weight: .7
11
12
13merge_method: ties
14base_model: MixtralOrochi8x7B
15parameters:
16 normalize: true
17 int8_mask: true
18dtype: float16
19
20
21
Detailed results can be found
here
