rbgo/Qwen3-gsm8k-GRPO
Text Generation • 4B • Updated
• 2
Rajdeep Borgohain
rbgo
AI & ML interests
Solving language barriers.
Recent Activity
liked
a Space 5 days ago
aion-intelligence/Queue-Penalty-Calculator reacted
to
ronantakizawa's
post with 👍 5 days ago
Introducing the github-codereview dataset: A compilation of 200k+ human-written code reviews from top OSS projects (React, Tensorflow, VSCode...).
I finetuned a Qwen2.5-Coder-32B-Instruct model with this dataset and saw significant improvements in generating better code fixes and review comments (4x improved BLEU-4, ROUGE-L, SBERT scores compared to base model).
#codereview #code #datasets
https://huggingface.co/datasets/ronantakizawa/github-codereview updated
a Space 21 days ago
aion-intelligence/Queue-Penalty-Calculator Organizations
rbgo/SmolLM2-1.7B-R1-Distilled-GRPO
Text Generation • 2B • Updated
• 1
rbgo/SmolLM2-1.7B-R1-Distilled
Text Generation • 2B • Updated
• 5
rbgo/SmolLM2-1-7B-Distill
Updated
rbgo/inferless-Llama-3-8B
Text Generation • 8B • Updated
• 2 • 2
rbgo/infer-Llama-3-8B
Text Generation • 8B • Updated
• 3
rbgo/gemma
Text Generation • 9B • Updated
• 5
rbgo/Super-phi-2-dpo
Text Generation • 3B • Updated
• 6 • 1