Ammar's picture

Ammar

Daemontatox

·

AI & ML interests

LLMS,VLLMS,SSMs

Recent Activity

updated a model about 10 hours ago

Daemontatox/HydraCoder

updated a model about 15 hours ago

Daemontatox/HydraMind

published a model about 18 hours ago

Daemontatox/HydraMind

View all activity

Organizations

upvoted a collection about 2 months ago

Common Pile v0.1 Raw Data

8TB of public domain and openly licensed text • 30 items • Updated Jun 6 • 18

upvoted 3 articles 2 months ago

Article

The Transformers Library: standardizing model definitions

By

and 3 others •

May 15

• 116

Article

CodeAgents + Structure: A Better Way to Execute Actions

By

and 1 other •

May 28

• 71

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

By

and 3 others •

May 23

• 152

upvoted a collection 2 months ago

SYNTHETIC-1

A collection of tasks & verifiers for reasoning datasets • 9 items • Updated 18 days ago • 62

upvoted a collection 3 months ago

Smoothie Qwen3

For more details, please visit https://github.com/dnotitia/smoothie-qwen • 9 items • Updated 9 days ago • 5

upvoted an article 5 months ago

Article

Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset

By

•

Feb 10

• 58

upvoted a paper 6 months ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 145

upvoted an article 6 months ago

Article

We now support VLMs in smolagents!

By

and 2 others •

Jan 24

• 108

upvoted a paper 6 months ago

LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs

Paper • 2501.06186 • Published Jan 10 • 66

upvoted a paper 7 months ago

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published Jul 1, 2024 • 63

upvoted a collection 7 months ago

QVQ

QVQ: Qwen models for visual reasoning • 7 items • Updated 12 days ago • 52

upvoted a paper 8 months ago

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published Dec 13, 2024 • 147

upvoted 2 collections 8 months ago

InternVL2.5

Better than InternVL 2.0 • 19 items • Updated Apr 20 • 92

Qwen2-VL

Vision-language model series based on Qwen2 • 16 items • Updated 12 days ago • 222

upvoted 2 collections 12 months ago

Highlighted work

My "greatest hits", sort of • 11 items • Updated Feb 14 • 4

Tools

IYKYK • 8 items • Updated Mar 24 • 2