Ujjwal Tyagi
Ujjwal-Tyagi
AI & ML interests
Chief Scientist at Shirova AI, focused on advancing open-source AI, Experienced in LLM fine-tuning, model architecture, and research, with a strong interest in building scalable and efficient models
Recent Activity
liked a dataset 4 days ago
lambda/hermes-agent-reasoning-traces liked a dataset 4 days ago
LucasFang/FLUX-Reason-6M updated a collection 4 days ago
Prompts CollectionsOrganizations
These are the datasets that can be used to finetune small LLMs to reach the level of the closed models and large open LLMs
-
Roman1111111/claude-opus-4.6-10000x
Viewer • Updated • 9.63k • 4.02k • 152 -
nohurry/Opus-4.6-Reasoning-3000x-filtered
Viewer • Updated • 2.33k • 9.82k • 534 -
Jackrong/Qwen3.5-reasoning-700x
Viewer • Updated • 633 • 7.22k • 102 -
Roman1111111/gpt-5.4-step-by-step-reasoning
Viewer • Updated • 1.5k • 1.01k • 49
These are the models that I collected and suitable for finetuning for various agentic task, coding and general task, which is easy to train and deploy
-
Ujjwal-Tyagi/sarvam-30b
Text Generation • 32B • Updated • 153 -
Ujjwal-Tyagi/Nemotron-Cascade-2-30B-A3B
Text Generation • 32B • Updated • 150 -
Ujjwal-Tyagi/Seed-OSS-36B-Instruct
Text Generation • 36B • Updated • 153 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 344k • • 1.26k
These are the datasets that can be used to finetune small LLMs to reach the level of the closed models and large open LLMs
-
Roman1111111/claude-opus-4.6-10000x
Viewer • Updated • 9.63k • 4.02k • 152 -
nohurry/Opus-4.6-Reasoning-3000x-filtered
Viewer • Updated • 2.33k • 9.82k • 534 -
Jackrong/Qwen3.5-reasoning-700x
Viewer • Updated • 633 • 7.22k • 102 -
Roman1111111/gpt-5.4-step-by-step-reasoning
Viewer • Updated • 1.5k • 1.01k • 49
These are the best coding corpuses to make the LLM more stronger to surpass proprietary ones, basically it can be used in both post and pre training.
These are the models that I collected and suitable for finetuning for various agentic task, coding and general task, which is easy to train and deploy
-
Ujjwal-Tyagi/sarvam-30b
Text Generation • 32B • Updated • 153 -
Ujjwal-Tyagi/Nemotron-Cascade-2-30B-A3B
Text Generation • 32B • Updated • 150 -
Ujjwal-Tyagi/Seed-OSS-36B-Instruct
Text Generation • 36B • Updated • 153 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 344k • • 1.26k