Models trained/used in the paper "DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging ( https://arxiv.org/abs/2407.01470)
NTU Miulab
university
AI & ML interests
None defined yet.
Collections
1
models
6
miulab/SalesBot2_CoT_lora_w_neg_wo_dup_chitchat_e10
Updated
•
703
miulab/SalesBot2_CoT_lora_w_neg
Updated
miulab/llama2-7b-alpaca-sft-10k
Text Generation
•
Updated
•
5
miulab/llama2-7b-ultrafeedback-rm
Text Classification
•
Updated
•
78
miulab/llama2-7b-oss-instruct
Text Generation
•
Updated
•
3
miulab/llama2-7b-magicoder-evol-instruct
Text Generation
•
Updated
•
3