google/gemma-3-1b-it
Text Generation
•
Updated
•
2.86M
•
385
alkinun
AtAndDev
AI & ML interests
LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..
Recent Activity
liked
a model
about 6 hours ago
google/gemma-3-1b-it
liked
a dataset
about 7 hours ago
Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B
liked
a model
2 days ago
Qwen/Qwen3-4B-FP8
Organizations
AtAndDev's activity
liked
a
model
about 6 hours ago
liked
a
dataset
about 7 hours ago
liked
2
models
2 days ago
liked
a
dataset
2 days ago
upvoted
a
paper
6 days ago
liked
a
model
27 days ago
upvoted
a
paper
27 days ago
reacted to
hesamation's
post with 👍🔥❤️
27 days ago
Post
2908
this paper has been blowing up
they train an open-source multimodal LLM (InternVL3) that can compete with GPT-4o and Claude 3.5 Sonnet by:
> training text and vision on a single stage
> a novel V2PE positional encoding
> SFT & mixed preference optimization
Paper: InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models (2504.10479)
> test-time scaling
they train an open-source multimodal LLM (InternVL3) that can compete with GPT-4o and Claude 3.5 Sonnet by:
> training text and vision on a single stage
> a novel V2PE positional encoding
> SFT & mixed preference optimization
Paper: InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models (2504.10479)
> test-time scaling
liked
a
dataset
about 1 month ago
replied to
Steven10429's
post
about 1 month ago
It seems like they randomly filter out some ppl for some reason...
upvoted
a
collection
about 1 month ago
liked
a
model
about 1 month ago
upvoted
a
paper
about 1 month ago
reacted to
AdinaY's
post with 👍
about 1 month ago
Post
1836
MAYE🎈a from-scratch RL framework for Vision Language Models, released by GAIR - an active research group from the Chinese community.
✨Minimal & transparent pipeline with standard tools
✨Standardized eval to track training & reflection
✨Open Code & Dataset
Code:
https://github.com/GAIR-NLP/MAYE?tab=readme-ov-file
Dataset:
ManTle/MAYE
Paper:
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme (2504.02587)
✨Minimal & transparent pipeline with standard tools
✨Standardized eval to track training & reflection
✨Open Code & Dataset
Code:
https://github.com/GAIR-NLP/MAYE?tab=readme-ov-file
Dataset:
ManTle/MAYE
Paper:
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme (2504.02587)
- 1 reply
