| .. |
|
prompt_templates
|
fix: llama4 tool use prompt fix (#2103)
|
2025-05-06 22:18:31 -07:00 |
|
quantization
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
vision
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
__init__.py
|
feat: introduce llama4 support (#1877)
|
2025-04-05 11:53:35 -07:00 |
|
args.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
chat_format.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
datatypes.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
ffn.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
generation.py
|
chore: make cprint write to stderr (#2250)
|
2025-05-24 23:39:57 -07:00 |
|
model.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
moe.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
preprocess.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
prompt_format.md
|
fix: llama4 tool use prompt fix (#2103)
|
2025-05-06 22:18:31 -07:00 |
|
prompts.py
|
chore: enable pyupgrade fixes (#1806)
|
2025-05-01 14:23:50 -07:00 |
|
tokenizer.model
|
feat(pre-commit): enhance pre-commit hooks with additional checks (#2014)
|
2025-04-30 11:35:49 -07:00 |
|
tokenizer.py
|
chore: remove usage of load_tiktoken_bpe (#2276)
|
2025-06-02 07:33:37 -07:00 |
