roma2025/Qwen3-VL-4B-Instruct-trl-grpo
Updated
Raman Saparkhan
roma2025
AI & ML interests
Fine-tuning LLMs, RAG.
Recent Activity
updated a dataset 28 days ago
roma2025/parsebench-table-track published a dataset 28 days ago
roma2025/parsebench-table-track updated a dataset about 1 month ago
roma2025/synthetic-table-benchOrganizations
