Alireza Mohammadshahi comments

Repositories
Issues
Comments

Results 5 comments of


                                            Alireza Mohammadshahi

LoRA MoE with k_proj, up_proj, down_proj

Hi, Thanks for opening the issue. Can you please provide more details on your implementation, and experts used for merging?

evaluation dataset

any updates?

Evaluation data of rule_qa for GPT4, GPT3.5, and Claude

Thanks for your response. I meant the evaluation of rule-based application: "Rule-application tasks were evaluated manually by a law-trained individual, who analyzed LLM responses for both correctness and analysis"

Evaluation data of rule_qa for GPT4, GPT3.5, and Claude

Thanks for the answer. Do you plan to release that human judgement for the evaluation?

Evaluation data of rule_qa for GPT4, GPT3.5, and Claude

Following up on this...