Soham Mandal

sohammandal01 's models 29

Sort:  Recently updated

sohammandal01/model_sft_dare_fv

2B • Updated Apr 5 • 3

sohammandal01/model_sft_fv

2B • Updated Apr 5 • 4

sohammandal01/part3_function_vector_artifacts

Updated Apr 5

sohammandal01/model_sft_dare_resta_0.7

Text Generation • 2B • Updated Apr 5 • 7

sohammandal01/model_sft_dare_resta_0.5

Text Generation • 2B • Updated Apr 5 • 6

sohammandal01/model_sft_dare_resta_0.3

Text Generation • 2B • Updated Apr 5 • 5

sohammandal01/model_sft_dare_resta_0.1

Text Generation • 2B • Updated Apr 5 • 6

sohammandal01/model_sft_resta

Text Generation • 2B • Updated Apr 5 • 6

sohammandal01/model_harmful_merged

Text Generation • 2B • Updated Apr 5 • 7

sohammandal01/model_sft_dare_0.7

Text Generation • 2B • Updated Apr 5 • 6

sohammandal01/model_sft_dare_0.5

Text Generation • 2B • Updated Apr 5 • 6

sohammandal01/model_sft_dare_0.3

Text Generation • 2B • Updated Apr 5 • 5

sohammandal01/model_sft_dare_0.1

Text Generation • 2B • Updated Apr 5 • 6

sohammandal01/model_sft_lora

Text Generation • 2B • Updated Apr 5 • 3

sohammandal01/sft-model

Text Generation • 2B • Updated Apr 5 • 6

sohammandal01/dare-model-0.7

Text Generation • 2B • Updated Apr 1 • 6

sohammandal01/dare-model-0.5

Text Generation • 2B • Updated Apr 1 • 5

sohammandal01/dare-model-0.3

Text Generation • 2B • Updated Apr 1 • 5

sohammandal01/dare-model-0.1

Text Generation • 2B • Updated Apr 1 • 6

sohammandal01/sft-lora

Updated Apr 1

sohammandal01/gpt2-aligned-ppo-lora-assignment

Updated Mar 3

sohammandal01/gpt2-aligned-ppo-prefix-assignment

Updated Mar 3

sohammandal01/gpt2-aligned-ppo-full-assignment

Text Generation • 0.4B • Updated Mar 3 • 6

sohammandal01/gpt2-aligned-dpo-qlora-assignment

Updated Mar 3

sohammandal01/gpt2-aligned-ppo-qlora-assignment

Updated Mar 2

sohammandal01/gpt2-aligned-dpo-lora-assignment

Updated Mar 2

sohammandal01/gpt2-aligned-dpo-prefix-assignment

Updated Mar 2

sohammandal01/bert-reward-model-assignment

Text Classification • 0.1B • Updated Mar 2 • 4

sohammandal01/gpt2-aligned-dpo-full-assignment

Text Generation • 0.4B • Updated Mar 2 • 7