HN Explorer

cs-fan-101

↗ HN profile [ 31.5 ms ] full profile
Karma
66
Created
March 28, 2023 (3y ago)
Submissions
0
  1. Cerebras Inference now runs Llama 3.1-70B at 2100 tokens/s (cerebras.ai)
    6 points 0
  2. Cerebras Launches the Fastest AI Inference (inference.cerebras.ai)
    13 points 2
  3. Sparse Maximal Update Parameterization (arxiv.org)
    2 points 0
  4. Cerebras Unveils Fastest AI Chip with Whopping 4T Transistors (cerebras.net)
    6 points 0
  5. Cerebras launches PyTorch-based library for sparse training (cerebras.net)
    2 points 0
  6. Jais – the world’s most advanced Arabic large language model

    Cerebras, G42's Inception, and MBZUAI are pleased to announce Jais, the world’s best-performing Arabic LLM. Jais is a 13B parameter model that was trained on a new 395 billion token Arabic-English-Code dataset. Jais…

    4 points 0
  7. Opentensor and Cerebras announce BTLM-3B-8K, a leading 3B param. language model (huggingface.co)
    9 points 2
  8. Cerebras and G42 Unveil Condor Galaxy 1, a 4 ExaFLOPS AI Supercomputer (cerebras.net)
    7 points 4
  9. Cerebras-GPT: Open Compute-Optimal Language Models Trained on Cerebras Cluster (arxiv.org)
    97 points 12