Hugging Face's logo
hanzlajavaid's picture
6 2 15

hanzlajavaid PRO

hanzla
mmfarabi's profile picture Innovationflow's profile picture ricardo102030's profile picture
·

AI & ML interests

Direct Preference Optimization, Supervised Finetuning, Stable Diffusion

Recent Activity

posted an update 10 days ago
Reinforcement learning can sometimes lead to emergent behavior through much simpler training setups compared to large scale pre-training. I explored this idea by running a small GRPO experiment on Qwen3.5 4B, and the results were pretty exciting. Hypothesis: improving visual mathematical reasoning may also improve the model’s ability to transcribe LaTeX from images. I wrote a short breakdown of the experiment here: https://hanzlajavaid.github.io/blog/grpo-experiment-exploring-emergent-properties/
updated a model 18 days ago
hanzla/Qwen3.5-4B-mathvista-GRPO
published a model 18 days ago
hanzla/Qwen3.5-4B-mathvista-GRPO
View all activity

Organizations

ZeroGPU Explorers's profile picture Journalists on Hugging Face's profile picture MLX Community's profile picture ModularityAI's profile picture Social Post Explorers's profile picture OpenAI gpt-oss Grants's profile picture