huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

use GPT2TokenizerFast by default

Browse Source
This commit is contained in:
OlivierDehaene 2024-03-29 18:46:28 +01:00
parent dcfefc425a
commit 275a61aae6
1 changed files with 22 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
server/text_generation_server/models/flash_dbrx.py
View File

@ -37,6 +37,17 @@ class FlashDbrx(FlashCausalLM):
else: else:
raise NotImplementedError("FlashDBRX is only available on GPU") raise NotImplementedError("FlashDBRX is only available on GPU")
try:
tokenizer = GPT2TokenizerFast.from_pretrained(
model_id,
revision=revision,
padding_side="left",
truncation_side="left",
trust_remote_code=trust_remote_code,
use_fast=True,
from_slow=False,
)
except:
try: try:
tokenizer = AutoTokenizer.from_pretrained( tokenizer = AutoTokenizer.from_pretrained(
model_id, model_id,