Stefano Fiorucci PRO

anakin87's activity

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

liked a dataset 4 days ago

sapienzanlp/dromedario-3-sft-dataset

Viewer • Updated 2 days ago • 939k • 339 • 9

liked a Space 9 days ago

Running

Featured

55

How to turn a game into an RL environment

🌍

55

From an idea to a trained 4B, with the dead ends left in

liked a model 9 days ago

anakin87/tiny-doom-defender

Reinforcement Learning • 1.1M • Updated 19 days ago • 36 • 5

liked a Space 10 days ago

Running

9

Tiny Doom Defender

👾

9

1.1M ModernBERT plays Doom in real time

liked a model 16 days ago

slseanwu/MIDI-LLM_Llama-3.2-1B

Text-to-Audio • 2B • Updated Jul 27 • 4.93k • 37

liked a Space 2 months ago

Running

Agents

10

Post Training Challenge

📈

10

Classifica & risultati della challenge!!

liked a Space 3 months ago

Running on Zero

Agents

3

Emma 5

🐣

3

Demo non ufficiale di un piccolo modello italiano

liked 3 models 3 months ago

Qwen/Qwen-AgentWorld-35B-A3B

Text Generation • 35B • Updated Jun 25 • 31.8k • 718

clark-labs/clark-air-sana-1.6b-1.58bit

Text-to-Image • 2B • Updated Jun 28 • 33 • 12

LiquidAI/LFM2.5-230M

Text Generation • 0.2B • Updated about 1 month ago • 58.2k • 295

liked 2 Spaces 3 months ago

Running

45

DeepResearch Bench

🔍

45

Explore DeepResearch benchmark leaderboards

Running

Featured

29

ColBERT Tool Selection

🧭

29

Send a request, the retriever pre-selects the right tools

liked a model 3 months ago

VAGOsolutions/SauerkrautLM-LFM2.5-GLiNER

Token Classification • Updated Jun 9 • 36 • 23

liked a dataset 5 months ago

VAGOsolutions/SauerkrautLM-Doom-MultiVec-31k

Viewer • Updated Apr 6 • 31.6k • 47 • 3

liked 3 models 5 months ago

anakin87/LFM2-2.6B-mr-tictactoe

Text Generation • 3B • Updated Apr 5 • 15 • 1

mradermacher/LFM2-2.6B-mr-tictactoe-GGUF

3B • Updated Apr 5 • 296 • 1

google/gemma-4-E4B-it

Any-to-Any • 8B • Updated Jul 20 • 4.47M • 1.57k

liked a Space 5 months ago

Running

Featured

93

Distilling 100B+ Models 40x Faster with TRL

📝

93

TRL distillation for 100B+ teachers, 40x faster

liked a dataset 5 months ago

lukawskikacper/openai-agent-traces

Traces • Updated Apr 9 • 1 • 69 • 2

liked a Space 5 months ago

Running on Zero

Agents

RL

5

Mr. Tic Tac Toe

⭕

5

Play Tic Tac Toe against a small RL tuned model