llama-models · Issues· 220 open

[Alignment & Behavior Bias].

Verify evals on Papers with Code

Request manual review for rejected Meta-Llama-3-8B-Instruct access

Help building my AI assistant Chancy from DRC using Llama 3.2

Request to reconsider rejected Hugging Face access for Llama-3.2-3B-Instruct

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

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

Llama 4 Mavericks

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

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

Android

Should Llama 3.3 prompt format be referencing 3.2?

Gender Bias in Professional Role Descriptions- Llama3.2

Tidak bisa buka chat

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