sagnik mukherjee

sagnikM 's models 15

Sort:  Recently updated

sagnikM/grpo_rmsprop_qwen3-8b_3k_seqlen

8B • Updated 21 days ago • 76

sagnikM/grpo_rmsprop_llama3p1_8b_3k_seqlen_1e-7

Text Generation • 8B • Updated 22 days ago • 111

sagnikM/grpo_rmsprop_qwen3_1p7b_3k_seqlen_1e-5

Text Generation • 2B • Updated 22 days ago • 132

sagnikM/grpo_rmsprop_qwen3_1p7b_3k_seqlen_1e-6

Text Generation • 2B • Updated 22 days ago • 120

sagnikM/grpo_sgd_qwen3-8b_3k_seqlen_momentum_0p9_1e-2

Text Generation • 8B • Updated Jan 17 • 71

sagnikM/grpo_sgd_llama3p1_8b_3k-seqlen_momentum_0p9_1e-3

Text Generation • 8B • Updated Jan 15 • 66

sagnikM/grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-2

Text Generation • 2B • Updated Jan 15 • 12

sagnikM/grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-1

Text Generation • 2B • Updated Jan 15 • 4

sagnikM/grpo_sgd_qwen3-8b_3k_seqlen

Text Generation • 8B • Updated Dec 25, 2025 • 45

sagnikM/grpo_adam_qwen3-8b_3k_seqlen

Text Generation • 8B • Updated Dec 25, 2025 • 38

sagnikM/grpo_adam_llama3.1_8b_instruct_adam

Text Generation • 8B • Updated Dec 22, 2025 • 1

sagnikM/ppo_sgd_qwen3_1.7b_1e-2_critic_adamW

Text Generation • 2B • Updated Dec 22, 2025 • 4

sagnikM/ppo_sgd_qwen3_1.7b_1e-2

Text Generation • 2B • Updated Dec 22, 2025 • 19

sagnikM/ppo_adam_qwen3_1.7b

Text Generation • 2B • Updated Dec 22, 2025 • 6

sagnikM/bert-finetuned-ner

Updated Apr 12, 2022