|
quantization
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
vision
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
__init__.py
|
feat: introduce llama4 support (#1877)
|
2025-04-05 11:53:35 -07:00 |
|
args.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
chat_format.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
datatypes.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
generation.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
model.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
moe.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
prompt_format.md
|
feat: introduce llama4 support (#1877)
|
2025-04-05 11:53:35 -07:00 |
|
prompts.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |
|
tokenizer.model
|
feat: introduce llama4 support (#1877)
|
2025-04-05 11:53:35 -07:00 |
|
tokenizer.py
|
several fixes
|
2025-04-07 10:31:20 -07:00 |