Isadora White's picture

7 1

Isadora White

izzcw

·

https://icwhite.github.io/website/

AI & ML interests

LLMs, Reinforcement Learning, agents, embodiment, multi-agent collaboration

Recent Activity

upvoted a paper 25 days ago

Group Sequence Policy Optimization

published a model 3 months ago

izzcw/dpo_model_3.1_8k

updated a model 3 months ago

izzcw/qwen_large_crafting_sft_success

View all activity

Organizations

izzcw 's models 26

izzcw/dpo_model_3.1_8k

izzcw/qwen_large_crafting_sft_success

Text Generation • 2B • Updated Jun 1 • 7

izzcw/large_crafting_sft_success

Text Generation • 2B • Updated Jun 1 • 4

izzcw/trajectory_crafting_dpo_pairs

izzcw/trajectory_crafting_dpo_pairs.json

izzcw/llama_3.1_large_crafting_sft_success

Text Generation • 8B • Updated May 31 • 7

izzcw/llama_3b_crafting_sft_success_new_mem

Text Generation • 3B • Updated May 27 • 5

izzcw/mini_llama_crafting_sft_success_new_mem

Text Generation • 1B • Updated May 27 • 11

izzcw/cooking_sft_fail_new_mem

Text Generation • 8B • Updated May 24 • 5

izzcw/crafting_sft_fail_new_mem

Text Generation • 8B • Updated May 24 • 5

izzcw/cooking_sft_success_new_mem

Text Generation • 8B • Updated May 22 • 4

izzcw/large_cooking_sft_success

Text Generation • 8B • Updated May 13 • 11 • 1

izzcw/large_cooking_sft_fail

8B • Updated May 11 • 5

izzcw/large_crafting_sft_fail

Text Generation • 8B • Updated May 8 • 5

izzcw/filtered_crafting_train_data_shorter_length

Text Generation • 8B • Updated May 8 • 6

izzcw/dpo_crafting_lora_from_sft

Updated May 1 • 1

izzcw/dpo_crafting_lora_from_base

Updated May 1 • 1

izzcw/dpo_crafting_lora

Updated May 1 • 1

izzcw/dpo_cooking

izzcw/filtered_crafting_train_data

8B • Updated Apr 28 • 4

izzcw/filtered_construction_train_data

8B • Updated Apr 28 • 3

izzcw/filtered_cooking_train_data

8B • Updated Apr 28 • 8

izzcw/llama_3_70b_lora_sft_construction

Updated Apr 11 • 1

izzcw/llama_3_70b_lora_sft_crafting

Updated Apr 11 • 1

izzcw/llama3_70b_lora_sft_cooking

Updated Apr 3 • 1

izzcw/final_combined_mc_data

Text Generation • 8B • Updated Mar 25 • 4