ftajwar/step-40
31B • Updated • 9
Fahim Tajwar
ftajwar
AI & ML interests
LLMs, RLHF
Recent Activity
updated a model 1 day ago
ftajwar/step-40 published a model 1 day ago
ftajwar/step-40 updated a model 1 day ago
ftajwar/step-30Organizations
ftajwar/step-30
31B • Updated • 10
ftajwar/step-20
31B • Updated • 8
ftajwar/step-10
31B • Updated • 11
ftajwar/uniagent-qwen3-30b-a3b-r2e-gspo
Updated
ftajwar/d24-climbmix-dolmino-midtrain-100b
Text Generation • 0.8B • Updated • 72
ftajwar/d24-climbmix-100b
Text Generation • 0.8B • Updated • 11
ftajwar/qwen3_1.7B_Base_GRPO_Polaris_1000_steps
Text Generation • 2B • Updated • 13
ftajwar/qwen3_1.7B_Base_MaxRL_Polaris_1000_steps
Text Generation • 2B • Updated • 16
ftajwar/qwen3_4B_Base_GRPO_Polaris_1000_steps
Text Generation • 4B • Updated • 7
ftajwar/qwen3_4B_Base_MaxRL_Polaris_1000_steps
Text Generation • 4B • Updated • 11
ftajwar/paprika_Meta-Llama-3.1-8B-Instruct_SFT_only
Text Generation • 8B • Updated • 7
ftajwar/paprika_Meta-Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 2