| .. |
|
__init__.py
|
207d2f80e9
Make code-llama and hf-tgi inference runnable as module
|
2 years ago |
|
chat_utils.py
|
6d9d48d619
Use apply_chat_template instead of custom functions
|
1 year ago |
|
checkpoint_converter_fsdp_hf.py
|
0e54f5634a
use AutoTokenizer instead of LlamaTokenizer
|
1 year ago |
|
llm.py
|
eeb45e5f2c
Updated model names for OctoAI
|
1 year ago |
|
model_utils.py
|
6ef9a78458
Fix issues with quantization_config == None
|
1 year ago |
|
prompt_format_utils.py
|
fd9f52f710
Modify prompt_format_utils with changes necessary for Llama Guard 3 (#1)
|
1 year ago |
|
safety_utils.py
|
f63ba19827
Fixing tokenizer used for llama 3. Changing quantization configs on safety_utils.
|
1 year ago |
Matthias Reso
6ef9a78458
Fix issues with quantization_config == None