Google Gemma-3-270m model variants on different fine-tuning
Swee.LOL
sweelol
·
AI & ML interests
Hub for Distilled Open Source LLMs
Organizations
-
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 143 -
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development
Paper • 2506.05010 • Published • 80 -
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Paper • 2506.05301 • Published • 58 -
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
Paper • 2505.16933 • Published • 34
Google Gemma-3-270m model variants on different fine-tuning
-
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 143 -
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development
Paper • 2506.05010 • Published • 80 -
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Paper • 2506.05301 • Published • 58 -
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
Paper • 2505.16933 • Published • 34
models
7
sweelol/gemma3-270m-pruned-baseline-50pc
Text Generation
•
Updated
sweelol/gemma3-270m-dolly-teacher
Text Classification
•
0.4B
•
Updated
sweelol/finetuned-pruned-gemma3-270m-dolly
Text Generation
•
0.4B
•
Updated
•
3
sweelol/gemma3-270m-pruned-base
Text Generation
•
0.3B
•
Updated
•
3
sweelol/kd-gemma3-pruned-dolly
Text Generation
•
0.4B
•
Updated
sweelol/lora-gemma3-270m-dolly
Text Generation
•
Updated
•
1
sweelol/pt-gemma3-270m-dolly
Text Generation
•
Updated
datasets
0
None public yet