Riddler

Riddler2024's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in empero-ai/Qwythos-9B-Claude-Mythos-5-1M 1 day ago

MTP (Multi-Token Prediction) not working with SGLang deployment

2

#8 opened 1 day ago by

Riddler2024

upvoted a collection 16 days ago

Cosmos3

Collection

Omnimodal World Models for Physical AI • 16 items • Updated about 22 hours ago • 132

liked a Space 6 months ago

Running on Zero

Agents

Featured

2.58k

Qwen Image Multiple Angles 3D Camera

🎥

2.58k

Transform image viewpoint with adjustable camera angles

liked a Space 8 months ago

Running on CPU Upgrade

Featured

3.22k

The Smol Training Playbook

📚

3.22k

The secrets to building world-class LLMs

New activity in jinaai/jina-embeddings-v4-vllm-retrieval 9 months ago

how can I use multi-vector embedding?

2

#4 opened 10 months ago by

Ayuan0105

updated a model 10 months ago

Riddler2024/colqwen-omni-v0.1-merged

Visual Document Retrieval • 4B • Updated Aug 26, 2025

published a model 10 months ago

Riddler2024/colqwen-omni-v0.1-merged

Visual Document Retrieval • 4B • Updated Aug 26, 2025

upvoted an article 11 months ago

view article

Article

Introducing ColQwen-Omni: Retrieve in every modality

• 

manu

•

Jul 17, 2025

• 77

liked a model 12 months ago

jinaai/jina-embeddings-v4-vllm-retrieval

Visual Document Retrieval • 4B • Updated Sep 17, 2025 • 269k • 32

New activity in jinaai/jina-embeddings-v3 over 1 year ago

ONNX model output

3

#38 opened over 1 year ago by

Riddler2024

updated a model over 1 year ago

Riddler2024/test

Updated Oct 15, 2024

New activity in jinaai/jina-clip-v1 almost 2 years ago

The textual ONNX models seem to have issues with more than 16 tokens on input

4

#22 opened almost 2 years ago by

ondrejnespor