thorirhrafn/icellama_domar_finetune_v3
Updated
Þórir Hrafn Harðarson
thorirhrafn
AI & ML interests
AI, machine learning and language technology
Recent Activity
updated
a dataset
9 days ago
thorirhrafn/mg_door_key_ball_env_state
published
a dataset
9 days ago
thorirhrafn/mg_door_key_ball_env_state
updated
a dataset
17 days ago
thorirhrafn/mg_door_key_ball_env_obs
Organizations
None yet
thorirhrafn/icellama_domar_pretuned_v3
Updated
thorirhrafn/gpt1B_DPO_model2
Updated
•
1
thorirhrafn/gpt1B_DPO_model
Updated
thorirhrafn/gpt1B_domar_finetune_1epoch
Updated
thorirhrafn/llama_DPO_model
Updated
thorirhrafn/gpt7B_DPO_model
Updated
thorirhrafn/gpt1B_reward_model2
Updated
thorirhrafn/gpt1B_domarsft_merged
Text Classification
•
1B
•
Updated
thorirhrafn/gpt1B_RLHF_model
Updated
thorirhrafn/gpt1B_rm_merged
Text Classification
•
1B
•
Updated
thorirhrafn/gpt1B_DPO_model_ver2
Updated
thorirhrafn/gpt1B_reward_test
Updated
thorirhrafn/gpt1B_reward_model
Updated
thorirhrafn/icellama_domar_pretuned_v2
Updated
thorirhrafn/gpt7B_domar_finetune
Updated
thorirhrafn/llama_domar_pretuned
Updated
thorirhrafn/icellama_domar_finetune
Updated
•
1
thorirhrafn/llama_domar_finetune
Updated
thorirhrafn/gpt1B_domar_finetune
Updated
thorirhrafn/icellama_domar_pretuned
Updated
thorirhrafn/gpt7b_domar_pretuned
Updated
thorirhrafn/sft_gpt1b_domar_pretuned
Updated
thorirhrafn/sft_gpt7b_domar_pretuned
Updated
thorirhrafn/gpt1B_domar_sum_v2
Updated
thorirhrafn/llama_ice_v4_domar
Updated
thorirhrafn/llama_ice_domar
Updated
thorirhrafn/gptsw3_icesum
Updated
thorirhrafn/gpt7B_domar_sum
Updated
thorirhrafn/ice_llama2_v4
Updated