This website requires JavaScript.
Explore
Help
Sign In
anodyine
/
vllm-omni
Watch
1
Star
0
Fork
0
Code
Issues
4
Pull Requests
2
Actions
Packages
Projects
Releases
Wiki
Activity
Files
eafc7c44c32747fe51b3356f137cfc57d64462d2
vllm-omni
/
vllm_omni
/
model_executor
/
models
T
History
Gaohan123
eafc7c44c3
fix error for pre-commit
2025-10-24 16:21:50 +08:00
..
__init__.py
fix error for pre-commit
2025-10-24 16:21:50 +08:00
qwen2_5_omni_talker.py
Qwen2.5-Omni: squash 5 commits (add components, refactor, load thinker embedding from weights, remove unused code)
2025-10-23 14:24:03 +08:00
qwen2_5_omni_thinker.py
Qwen2.5-Omni: squash 5 commits (add components, refactor, load thinker embedding from weights, remove unused code)
2025-10-23 14:24:03 +08:00
qwen2_5_omni_token2wav.py
Qwen2.5-Omni: squash 5 commits (add components, refactor, load thinker embedding from weights, remove unused code)
2025-10-23 14:24:03 +08:00
qwen2_5_omni.py
Enhance Qwen2.5-Omni model by defining TALKER_CODEC_EOS_TOKEN_ID and TALKER_CODEC_BOS_TOKEN_ID constants. Update audio generation logic to use these constants for improved clarity and maintainability. Refactor tensor initialization to utilize the talker's hidden size. Update comments for better understanding and consistency.
2025-10-24 10:02:51 +08:00
qwen2_old.py
Qwen2.5-Omni: squash 5 commits (add components, refactor, load thinker embedding from weights, remove unused code)
2025-10-23 14:24:03 +08:00
registry.py
fix error for pre-commit
2025-10-24 16:21:50 +08:00
utils.py
Qwen2.5-Omni: squash 5 commits (add components, refactor, load thinker embedding from weights, remove unused code)
2025-10-23 14:24:03 +08:00