Ujjwal Tyagi's picture

Building on HF

Ujjwal Tyagi

Ujjwal-Tyagi

·

AI & ML interests

Love open-source agentic AI | Senior ML Engineer & AI Researcher | Passionate about AI Safety & Ethics

Recent Activity

replied to danielhanchen's post 2 days ago

You can now run Qwen3.5 locally! 💜 Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2. GGUF: https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s. Guide: https://unsloth.ai/docs/models/qwen3.5

liked a model 2 days ago

prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX

upvoted a collection 2 days ago

View all activity

Organizations

New activity in moonshotai/Kimi-K2.5 11 days ago

Model parameters confusion

#67 opened 11 days ago by

New activity in nyuuzyou/suno 14 days ago

Separate Indian Song Dataset would be helpful too

#6 opened 14 days ago by

New activity in TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill 27 days ago

Great Work

#1 opened 27 days ago by

New activity in baichuan-inc/Baichuan-M3-235B about 1 month ago

Language Mixing Problems

#1 opened about 1 month ago by

New activity in 169Pi/Alpie-Core about 1 month ago

Python SDK & Hosted API now available for Alpie Core (4-bit, 32B)

#1 opened about 1 month ago by

commented 3 papers 3 months ago

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

Paper • 2511.04962 • Published Nov 7, 2025 • 57 •

Jailbreaking in the Haystack

Paper • 2511.04707 • Published Nov 5, 2025 • 5 •

The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms

Paper • 2511.04217 • Published Nov 6, 2025 • 17 •