·
AI & ML interests
None yet
Organizations
sravanthib/new-lr-3e-6-llama-3-2-1b-model_testing
Updated
sravanthib/meeting-llama-3-2-1b-custom-1000-steps-logging-old-deepspeed
Updated
sravanthib/llama-3-2-1b-custom-100-steps-logging-old-deepspeed
Text Generation
• Updated • 1
sravanthib/llama-3-2-1b-custom-100-steps-logging
Text Generation
• Updated • 1
sravanthib/new-300-steps-DeepSeek-R1-Distill-Qwen-7B
Text Generation
• Updated • 3
sravanthib/DeepSeek-R1-Distill-Qwen-7B-squad-nemo-replicaa
Text Generation
• Updated • 1
sravanthib/accel_deepspeed_llama_3_3b
Updated
sravanthib/fsdp2_llama_3_3b
Updated
sravanthib/testing_deepspeed-new-llama-3-3b
Updated
sravanthib/custom_fsdp2-500-qwen-2-5-7b_testing-without-deepspeed
Updated
sravanthib/testing_fsdp2_qwen2-5-7b
Text Generation
• Updated • 1
sravanthib/custom_ddp_testing-without-deepspeed
Updated
sravanthib/testing-without-deepspeed
Text Generation
• Updated • 1
sravanthib/multi-gpu-llama-3-2-1b-40k-1e-4-custom-sft-2048-seqlen
sravanthib/qwen_model_testing
Text Generation
• Updated • 1
sravanthib/single-gpu-llama-3-2-1b-40k-1e-4-custom-sft-2048-seqlen
Updated
sravanthib/new-single-gpu-llama-3-2-1b-40k-1e-4-custom-sft
Updated
sravanthib/single-node-single-gpu-qwen-custom-sft
sravanthib/refactored-code-llama-3-2-3b
3B • Updated • 1
sravanthib/qwen-7b-squad-lora
sravanthib/qwen-32b-squad-lora
Updated
sravanthib/qwen-72b-squad-lora
Updated
sravanthib/testing_refactored_code_llama-3-1-3b-1000-steps
sravanthib/checking-refactored-code
Updated
sravanthib/final_one_custom_llama_1000_steps
3B • Updated