In a Training Loop 🔄

49 59 173

Stefano Fiorucci PRO

anakin87

AI & ML interests

Language Models: orchestration, post-training, GRPO, synthetic data... Contributing to Haystack LLM framework 🏗️

Recent Activity

updated a model 8 days ago

anakin87/Qwen3-0.6B-tictactoe

published a model 8 days ago

anakin87/Qwen3-0.6B-tictactoe

View all activity

Organizations

upvoted a collection about 1 month ago

INTELLECT-3

Collection

INTELLECT-3: A 100B+ MoE trained with large-scale RL • 4 items • Updated Nov 28 • 11

upvoted a collection about 2 months ago

SYNTH

Collection

Fully generalist synthetic dataset and SOTA small reasoners • 3 items • Updated Nov 10 • 11

upvoted a paper 2 months ago

Extracting alignment data in open models

Paper • 2510.18554 • Published Oct 21 • 9

upvoted an article 2 months ago

Article

Extract Text and Knowledge from Images with Open Vision Language Models

Oct 23

•

upvoted a collection 3 months ago

IFBench

Collection

Datasets for IFBench benchmark and paper! • 3 items • Updated 7 days ago • 10

upvoted an article 3 months ago

Article

Smol2Operator: Post-Training GUI Agents for Computer Use

Sep 23

•

134

upvoted 2 articles 4 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

Sep 4

•

267

Article

Exploring Environments Hub: Your Language Model needs better (open) environments to learn

Sep 4

•

upvoted a collection 4 months ago

EmbeddingGemma

Collection

3 items • Updated Sep 11 • 105

upvoted an article 4 months ago

Article

Some Safety and Security tests using LlamaGuard 4 12B and PromptGuard2

Aug 28

•

upvoted an article 5 months ago

Article

Vision Language Model Alignment in TRL ⚡️

Aug 7

•

104

upvoted a paper 5 months ago

Mergenetic: a Simple Evolutionary Model Merging Library

Paper • 2505.11427 • Published May 16 • 14

upvoted a collection 6 months ago

T5Gemma

Collection

32 items • Updated Jul 10 • 78

upvoted an article 6 months ago

Article

cocogold: training Marigold for text-grounded segmentation

Jul 8

•

upvoted an article 8 months ago

Article

Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs

May 7

•

upvoted a collection 8 months ago

Qwen Scheduler GRPO

Collection

Train a SLM to create a schedule from a list of events and priorities - Article: https://t.ly/-Dejx - Code: https://t.ly/1J_VG • 2 items • Updated Oct 25 • 4

upvoted an article 8 months ago

Article

I trained a Language Model to schedule events with GRPO!

Apr 29

•

upvoted 2 articles 10 months ago

Article

Training a Gemma 2 2B-IT for Reasoning with GRPO

Mar 18

•

Article

Argunauts Training Phase II: Selfplay Finetuning Line-By-Line

Feb 19

•

upvoted an article 11 months ago

Article

Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset

Feb 10

•

Stefano Fiorucci PRO

AI & ML interests

Recent Activity

Organizations

anakin87's activity

Extract Text and Knowledge from Images with Open Vision Language Models

Smol2Operator: Post-Training GUI Agents for Computer Use

Welcome EmbeddingGemma, Google's new efficient embedding model

Exploring Environments Hub: Your Language Model needs better (open) environments to learn

Some Safety and Security tests using LlamaGuard 4 12B and PromptGuard2

Vision Language Model Alignment in TRL ⚡️

cocogold: training Marigold for text-grounded segmentation

Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs

I trained a Language Model to schedule events with GRPO!

Training a Gemma 2 2B-IT for Reasoning with GRPO

Argunauts Training Phase II: Selfplay Finetuning Line-By-Line

Fine-tune Deepseek-R1 with a Synthetic Reasoning Dataset