Zijie Tian e09a2a5b10 ✨ feat: add Qwen2/2.5 model support ...

Separate Qwen2 from Qwen3 implementation:
- Qwen2: Uses QKV bias, no QK norm
- Qwen3: Has optional QK norm when no bias

Tested with Qwen2.5-7B-Instruct-1M, RULER niah_single_1 passed.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-28 13:44:32 +08:00

..

__init__.py

✨ feat: add Qwen2/2.5 model support

2026-01-28 13:44:32 +08:00

glm4.py

✨ feat: add GLM-4-9B-Chat-1M model support

2026-01-28 13:15:57 +08:00

llama.py

[claudesquad] update from 'add-llama-1' on 10 Jan 26 21:03 CST

2026-01-10 21:03:45 +08:00

qwen2.py

✨ feat: add Qwen2/2.5 model support

2026-01-28 13:44:32 +08:00

qwen3.py

✨ feat: add Qwen2/2.5 model support

2026-01-28 13:44:32 +08:00

registry.py

[claudesquad] update from 'add-llama-1' on 10 Jan 26 21:03 CST

2026-01-10 21:03:45 +08:00