| .. |
|
__init__.py
|
207d2f80e9
Make code-llama and hf-tgi inference runnable as module
|
2 лет назад |
|
chat_utils.py
|
e554c1c8bf
The tokenizer will not add eos_token by default
|
2 лет назад |
|
checkpoint_converter_fsdp_hf.py
|
ce9501f22c
remove relative imports
|
2 лет назад |
|
llm.py
|
a404c9249c
Notebook to demonstrate using llama and llama-guard together using OctoAI
|
1 год назад |
|
model_utils.py
|
d51d2cce9c
adding sdpa for flash attn
|
1 год назад |
|
prompt_format_utils.py
|
3e710f71f8
renaming the prompt format file to conform to repo standards
|
1 год назад |
|
safety_utils.py
|
c0886a0a89
Fixing typo in self
|
1 год назад |
varunfb
a404c9249c
Notebook to demonstrate using llama and llama-guard together using OctoAI