DedeProGames/lm-tetris-arena-results
Updated • 10.8k • 2
DedeProGames PRO
DedeProGames
AI & ML interests
Agentic & Coding finetune, Decoder-Onlys from Scratch, Image LoRAs, AI Researcher
Recent Activity
liked a model about 9 hours ago
SupraLabs/Supra2.1-Ultra reacted to theirpost with 🧠 about 9 hours ago
Meet Supra2.5-Ultra-Preview-001. 230M parameters, ~40.4B training tokens.
SupraLabs has released the first preview of its Supra2.5-Ultra family: a compact, Llama-style base model for text completion and small-model experimentation.
What's inside?
• 230M parameters
• 32 transformer layers
• 2,048-token context window
• Grouped Query Attention: 12 attention heads, 4 KV heads
• 49,152-token vocabulary
• SwiGLU activation, RoPE and tied embeddings
• BF16 weights and Hugging Face Transformers support
• Apache 2.0 license
Training
The model was trained on approximately 40.4B tokens from FineWeb-Edu, DCLM-Baseline and FineMath using a single A100 SXM.
Reported zero-shot results
• HellaSwag: 37.18% normalized accuracy
• PIQA: 65.78% accuracy
• ARC-Easy: 57.11% accuracy
• ARC-Challenge: 26.28% normalized accuracy
Want to experiment?
Code on REPO.
Model, weights and usage example:
SupraLabs/Supra2.5-Ultra-Preview-001 reacted to theirpost with 🚀 about 9 hours ago
Meet Supra2.5-Ultra-Preview-001. 230M parameters, ~40.4B training tokens.
SupraLabs has released the first preview of its Supra2.5-Ultra family: a compact, Llama-style base model for text completion and small-model experimentation.
What's inside?
• 230M parameters
• 32 transformer layers
• 2,048-token context window
• Grouped Query Attention: 12 attention heads, 4 KV heads
• 49,152-token vocabulary
• SwiGLU activation, RoPE and tied embeddings
• BF16 weights and Hugging Face Transformers support
• Apache 2.0 license
Training
The model was trained on approximately 40.4B tokens from FineWeb-Edu, DCLM-Baseline and FineMath using a single A100 SXM.
Reported zero-shot results
• HellaSwag: 37.18% normalized accuracy
• PIQA: 65.78% accuracy
• ARC-Easy: 57.11% accuracy
• ARC-Challenge: 26.28% normalized accuracy
Want to experiment?
Code on REPO.
Model, weights and usage example:
SupraLabs/Supra2.5-Ultra-Preview-001Organizations
