Thomas Zeng

mtzig 's models 115

Sort:  Recently updated

mtzig/reverse_add_replicate_eval17_corruptedfull

0.0B • Updated Mar 19 • 4

mtzig/reverse_add_replicate_eval17_corrupted

0.0B • Updated Mar 19 • 2

mtzig/reverse_add_replicate_eval17_SGD_largelr

0.0B • Updated Mar 19 • 2

mtzig/reverse_add_replicate_eval17_SGD

0.0B • Updated Mar 19 • 2

mtzig/reverse_add_replicate_eval18

0.0B • Updated Mar 19 • 2

mtzig/reverse_add_replicate_eval30

0.0B • Updated Mar 19 • 2

mtzig/reverse_add_replicate_eval20

0.0B • Updated Mar 19 • 2

mtzig/reverse_add_replicate

0.0B • Updated Mar 19 • 2

mtzig/gpt2_cfg_add_8_to_64_train_attn

Updated Feb 19

mtzig/gpt2_cfg_add_8_to_32_train_mlp

Updated Feb 19

mtzig/gpt2_cfg_add_8

0.0B • Updated Feb 19 • 3

mtzig/lge_tests_prelim

0.0B • Updated Feb 18 • 5

mtzig/lge_test

0.0B • Updated Feb 17 • 3

mtzig/mmlu_small_noaugs_llama_lora

Updated Jan 21

mtzig/prm800k_llama_lora

Updated Dec 26, 2024 • 433

mtzig/prm800k_qwen_alt_lora

Updated Dec 23, 2024 • 3

mtzig/qwen_debug_test

Updated Dec 21, 2024 • 3

mtzig/prm800k_qwen_lora

Updated Dec 21, 2024

mtzig/prm800k_llama_joint_checkpoint8500

8B • Updated Dec 19, 2024 • 3

mtzig/prm800k_llama_joint_checkpoint4500

8B • Updated Dec 14, 2024 • 4

mtzig/joint_debug_test

Updated Dec 7, 2024 • 2

mtzig/v3c_llama_lora

Updated Dec 5, 2024 • 3

mtzig/prm800k_mistral_full_1203_re

Text Generation • 7B • Updated Dec 4, 2024 • 10

mtzig/prm800k_llama_debug_full

8B • Updated Dec 4, 2024 • 3

mtzig/prm800k_mistral_full_1203

Updated Dec 3, 2024

mtzig/prm800k_llama_full

Updated Dec 3, 2024

mtzig/prm800k_llama_aws_full

Updated Dec 3, 2024

mtzig/prm800k_mistral_full_1202

Updated Dec 2, 2024

mtzig/v3c_mistral_lora_lastn

Updated Dec 1, 2024 • 4

mtzig/v3d_mistral_lora

Updated Nov 30, 2024 • 3