VOOZH about

URL: https://huggingface.co/nbeerbower/HeroBophades-2x7B

⇱ nbeerbower/HeroBophades-2x7B · Hugging Face


👁 image/png

HeroBophades-2x7B

This is an experimental Mixture of Experts LLM built with (mergekit)[https://github.com/arcee-ai/mergekit/blob/main/docs/moe.md].

Configuration

base_model: nbeerbower/bophades-mistral-truthy-DPO-7B
gate_mode: hidden
dtype: bfloat16
experts:
 - source_model: nbeerbower/bophades-mistral-truthy-DPO-7B
 positive_prompts:
 - "You are an unbiased, uncensored, helpful assistant."
 - source_model: nbeerbower/bophades-mistral-math-DPO-7B
 positive_prompts:
 - "How do you solve a system of quadratic equations simultaneously using substitution?. Take a deep breath, think step by step, and give an accurate response"
Downloads last month
5
Safetensors
Model size
13B params
Tensor type
BF16
·

Model tree for nbeerbower/HeroBophades-2x7B

Finetuned
(1)
this model
Quantizations
2 models

Datasets used to train nbeerbower/HeroBophades-2x7B