| .. |
|
__init__.py
|
207d2f80e9
Make code-llama and hf-tgi inference runnable as module
|
hai 1 ano |
|
chat_utils.py
|
6d9d48d619
Use apply_chat_template instead of custom functions
|
hai 1 ano |
|
checkpoint_converter_fsdp_hf.py
|
0e54f5634a
use AutoTokenizer instead of LlamaTokenizer
|
hai 11 meses |
|
llm.py
|
eeb45e5f2c
Updated model names for OctoAI
|
hai 11 meses |
|
model_utils.py
|
e2f77dbc21
fix quant config
|
hai 8 meses |
|
prompt_format_utils.py
|
fd9f52f710
Modify prompt_format_utils with changes necessary for Llama Guard 3 (#1)
|
hai 9 meses |
|
safety_utils.py
|
4be3eb0d17
Updates HF model_ids and readmes for 3.1
|
hai 9 meses |
Suraj Subramanian
935f66f7d0
Merge branch 'main' into inference_changes