Mungert/Qwen2.5-VL-3B-Instruct-GGUF
Image-Text-to-Text
•
3B
•
Updated
•
5.57k
•
21
cstr
cstr
AI & ML interests
None yet
Recent Activity
liked
a model
7 days ago
Mungert/Qwen2.5-VL-3B-Instruct-GGUF
liked
a model
7 days ago
rednote-hilab/dots.ocr
liked
a dataset
24 days ago
DeepMount00/italian_conversations
Organizations
liked
2
models
7 days ago
liked
a
dataset
24 days ago
liked
a
Space
24 days ago
liked
a
model
30 days ago
liked
2
models
2 months ago
updated
a
model
2 months ago
published
a
model
2 months ago
liked
a
model
2 months ago
mlx conversion
#5 opened 2 months ago
by
cstr
updated
a
model
2 months ago
published
a
model
2 months ago
liked
3
models
3 months ago
reacted to
hesamation's
post with 👀
4 months ago
Post
2932
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
2
models
4 months ago
liked
a
dataset
4 months ago