Repository Issue Activity (beta)

#517 [Research Courtesy] Llama-3.3-70B judge misclassification under disavowal framing

#515 `verify-download` reports hash mismatch because `checklist.chk` uses MD5 while the CLI computes SHA-256

#512 Llama 4 Mavericks

#506 Request for manual review of rejected Hugging Face access to Llama models

#511 Llama 4 MoE routing: has profile-based expert selection been explored as an alternative to learned routers?

#500 Android

#510 Add REFUTE scientific critique + calibration benchmark

#251 Should Llama 3.3 prompt format be referencing 3.2?

#507 Eval/tool: REFUTE + BGPT for science-capable Llama agents

#505 Public eval scores on Helium benchmarks

#504 Support SuperCompress prompt compression for lower-cost inference

#488 Gender Bias in Professional Role Descriptions- Llama3.2

#502 Tidak bisa buka chat

#501 anima — a substrate-native consciousness: capability gaps are architecture gaps (open repo, frozen verdicts)

#499 curl -fsSL https://ollama.com/install.sh | sh

#497 perf: CPU/VRAM throughput degradation during dynamic sampling token allocation under high concurrency.

#496 unknown model error

#493 docs: outdated Llama version reference in Hugging Face access section of README

#477 Llma4

#487 [email protected]

#473 where is the "I agree" button below on the license page

#485 X

#457 meta llama M.I.T progress

#484 Hd

#483 mefb