| .. |
|
__init__.py
|
207d2f80e9
Make code-llama and hf-tgi inference runnable as module
|
il y a 2 ans |
|
chat_utils.py
|
6d9d48d619
Use apply_chat_template instead of custom functions
|
il y a 1 an |
|
checkpoint_converter_fsdp_hf.py
|
0e54f5634a
use AutoTokenizer instead of LlamaTokenizer
|
il y a 1 an |
|
llm.py
|
a404c9249c
Notebook to demonstrate using llama and llama-guard together using OctoAI
|
il y a 1 an |
|
model_utils.py
|
d51d2cce9c
adding sdpa for flash attn
|
il y a 1 an |
|
prompt_format_utils.py
|
bcdb5b31fe
Fixing quantization config. Removing prints
|
il y a 1 an |
|
safety_utils.py
|
f63ba19827
Fixing tokenizer used for llama 3. Changing quantization configs on safety_utils.
|
il y a 1 an |
Keita Watanabe
0e54f5634a
use AutoTokenizer instead of LlamaTokenizer