suv11235/toy-anchor-lora
Updated
• 3
Suvajit Majumder
suv11235
AI & ML interests
LLM finetuning, deep learning theory, ML applications in physics and maths
Recent Activity
new activity
17 days ago
suv11235/chandra-grpo-lora-num_gen12-ep10:Finetuning `chandra` updated
a model about 1 month ago
suv11235/toy-anchor-lora published
a model about 1 month ago
suv11235/toy-anchor-lora Organizations
suv11235/qwen3vl-supervised-lora-eval
Text Generation • Updated
• 1
suv11235/chandra-supervised-lora-gemini-full-5epochs
Text Generation • Updated
• 2
suv11235/chandra-supervised-lora-gemini
Text Generation • Updated
• 3
suv11235/mtsa-rlvr-stubborn-singular-cp40
Text Generation • Updated
suv11235/mtsa-rlvr-focused-cp6
Text Generation • Updated
suv11235/mtsa-rlvr-representation-loss-llama-3.1-8b
Updated
suv11235/vanilla-tar-baseline-llama-3.1-8b
Updated
suv11235/mtsa-rlvr-scaling-baseline-llama-3.1-8b
Updated
suv11235/mtsa-extreme-tar-v1-llama-3.1-8b
Updated
suv11235/grpo_training_easy_continued
Updated
suv11235/parsed-line-items-easy-docs-5ep
Updated
suv11235/red_team_model_SFT_mtsa
Text Generation • Updated
• 305
suv11235/all_easy_finetuned_30steps
Updated
suv11235/all_easy_finetuned_20steps
Updated
suv11235/qwen3-vl-8b-grpo-lora-1-shot
Text Generation • Updated
suv11235/chandra-grpo-5ep-4doc-full-extraction
Text Generation • 8B • Updated
• 1
suv11235/chandra-grpo-full-ft-10epoch
Image-Text-to-Text • Updated
suv11235/mtsa-attacker-qwen2.5-7b
Text Generation • Updated
suv11235/chandra-grpo-lora-num_gen12-ep10
Text Generation • Updated
• 5
suv11235/chandra-grpo-lora-10-ep-50-docs
Updated
• 6
suv11235/olmOCR-7B-grpo-v6
Image-Text-to-Text • 8B • Updated
• 1
suv11235/olmOCR-7B-grpo-v5
Updated
suv11235/tokenbuncher-qwen-3b-step500
3B • Updated
suv11235/tokenbuncher-qwen-3b-step400
3B • Updated
suv11235/tokenbuncher-qwen-3b-step200
3B • Updated
suv11235/tokenbuncher-qwen-3b-step100
3B • Updated
suv11235/tokenbuncher-qwen-3b-step300
3B • Updated
suv11235/qwen-3b-attacked-final
3B • Updated
• 1
suv11235/qwen-3b-test-push
3B • Updated