arxiv:2403.02745
Son The Nguyen
sonthenguyen
AI & ML interests
Large language models and Vision language models
Organizations
None yet
Papers
1
models
18
sonthenguyen/zephyr-sft-bnb-4bit-DPO-dismissive_mtbc-252steps
Text Generation
•
Updated
•
16
sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbr-180steps
Text Generation
•
Updated
•
18
sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbc-213steps
Text Generation
•
Updated
•
20
sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-180steps
Text Generation
•
Updated
•
47
sonthenguyen/zephyr-sft-bnb-4bit-DPO-mtbo-137steps
Text Generation
•
Updated
•
15
sonthenguyen/testdpounsloth
Text Generation
•
Updated
•
13
sonthenguyen/OpenHermes-2.5-Mistral-7B-DPO-mtbo
Text Generation
•
Updated
•
17
sonthenguyen/Qwen2.5-dpo-original
Text Generation
•
Updated
•
9
sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered
Text Generation
•
Updated
•
55
•
1
sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-original-v3
Text Generation
•
Updated
•
8
•
2
datasets
None public yet