Thomas Zeng

mtzig 's models 152

Sort:  Recently updated

mtzig/reverse_add_replicate_eval17_small_1layer_d1_50

55 • Updated Mar 24, 2025 • 1

mtzig/reverse_add_replicate_eval17_small_1layer_d1_20

55 • Updated Mar 24, 2025 • 1

mtzig/reverse_add_replicate_eval17_small_1layer_d2

55 • Updated Mar 24, 2025

mtzig/maze_replicate_10

10.7M • Updated Mar 22, 2025 • 1

mtzig/maze_replicate_10_test

10.7M • Updated Mar 22, 2025 • 1

mtzig/reverse_add_replicate_eval17_small_1layer

1.11k • Updated Mar 20, 2025 • 1

mtzig/reverse_add_replicate_eval17_small

7.04k • Updated Mar 20, 2025 • 1

mtzig/reverse_add_replicate_eval17_corruptedfull

10.7M • Updated Mar 19, 2025 • 5

mtzig/reverse_add_replicate_eval17_corrupted

10.7M • Updated Mar 19, 2025

mtzig/reverse_add_replicate_eval17_SGD_largelr

10.7M • Updated Mar 19, 2025

mtzig/reverse_add_replicate_eval17_SGD

10.7M • Updated Mar 19, 2025

mtzig/reverse_add_replicate_eval18

10.7M • Updated Mar 19, 2025

mtzig/reverse_add_replicate_eval30

10.7M • Updated Mar 19, 2025 • 1

mtzig/reverse_add_replicate_eval20

10.7M • Updated Mar 19, 2025

mtzig/reverse_add_replicate

10.7M • Updated Mar 19, 2025 • 1

mtzig/gpt2_cfg_add_8_to_64_train_attn

Updated Feb 19, 2025

mtzig/gpt2_cfg_add_8_to_32_train_mlp

Updated Feb 19, 2025

mtzig/gpt2_cfg_add_8

10.7M • Updated Feb 19, 2025

mtzig/lge_tests_prelim

7.04k • Updated Feb 18, 2025 • 3

mtzig/lge_test

880 • Updated Feb 17, 2025 • 1

mtzig/mmlu_small_noaugs_llama_lora

Updated Jan 21, 2025

mtzig/prm800k_llama_lora

Updated Dec 26, 2024 • 147

mtzig/prm800k_qwen_alt_lora

Updated Dec 23, 2024

mtzig/qwen_debug_test

Updated Dec 21, 2024

mtzig/prm800k_qwen_lora

Updated Dec 21, 2024

mtzig/prm800k_llama_joint_checkpoint8500

8B • Updated Dec 19, 2024

mtzig/prm800k_llama_joint_checkpoint4500

8B • Updated Dec 14, 2024

mtzig/joint_debug_test

Updated Dec 7, 2024

mtzig/v3c_llama_lora

Updated Dec 5, 2024

mtzig/prm800k_mistral_full_1203_re

Text Generation • 7B • Updated Dec 4, 2024