AI & ML interests
None yet
Organizations
None yet
sravanthib/llama-testing-wf
Updated
sravanthib/llama-3-2-1b-lora
Updated
sravanthib/llama-3-2-1b-finetuned
Updated
sravanthib/Nemo-RL-qwen-1-5b-1000steps
sravanthib/custom-accele-Qwen-4b-500-steps
4B
•
Updated
sravanthib/custom_accelerate-Qwen-4b-wd-warmup-same-as-nemo
Updated
sravanthib/custom_accelerate-deepseek-v2-Lite-wd-warmup-same-as-nemo
Updated
sravanthib/custom-DDP-deepseek-coder-1000-steps
1B
•
Updated
sravanthib/custom_accelerate-deepseek-coder-1-5b-20k-wd-warmup-same-as-nemo
Updated
sravanthib/accelerate-custom-DDP-qwen-1-5b-instruct-1000-ws-50
2B
•
Updated
sravanthib/custom_accelerate-Qwen1.5b-20k-wd-warmup-same-as-nemo
Text Generation
•
Updated
•
2
sravanthib/custom-accelerate-ddp-ws-50-exact-config-1000
1B
•
Updated
•
1
sravanthib/custom_accelerate-llama-20k-wd-warmup-same-as-nemo
Text Generation
•
Updated
sravanthib/accelerate-custom-nemo-config-llama
1B
•
Updated
•
1
sravanthib/custom-auto-llama-stage2
1B
•
Updated
•
1
sravanthib/stage-2-customauto-config-llama-3-2-custom-1000-steps-logging-old-deepspeed
Text Generation
•
Updated
sravanthib/custom-stage-2-llama-20k
1B
•
Updated
sravanthib/stage-2-custom-llama-3-2-custom-1000-steps-logging-old-deepspeed
Text Generation
•
Updated
•
1
sravanthib/custom-accelerate-llama-3-1-1b-20k
Updated
sravanthib/custom-20k-1e-4-qwen-1-5b-instruct
2B
•
Updated
sravanthib/lr-20k-stage-0-1e-4-Qwen2-5-1-5-B-Instruct-custom-1000-steps-logging-old-deepspeed
Text Generation
•
Updated
sravanthib/custom-new-20k-llama-3-1b
1B
•
Updated
•
1
sravanthib/custom-1e-4-20k-1000
1B
•
Updated
sravanthib/lr-20k-stage-0-1e-4-llama-3-2-1b-custom-1000-steps-logging-old-deepspeed
Text Generation
•
Updated
sravanthib/custom-1e-4-llama-3-1b
1B
•
Updated
sravanthib/lr-1e-4-llama-3-2-1b-custom-1000-steps-logging-old-deepspeed
Text Generation
•
Updated
sravanthib/custom-new-1000-3e-4
1B
•
Updated
sravanthib/lr-3e-6-llama-3-2-1b-custom-1000-steps-logging-old-deepspeed
Text Generation
•
Updated
sravanthib/custom-3e-6-llama-3-2-1b
1B
•
Updated