Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

enh: enable CodeLlama #48

Merged
merged 2 commits into from
Nov 21, 2023
Merged

enh: enable CodeLlama #48

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c35af5b
enh: enable CodeLlama
geoffreyangus Nov 21, 2023
8b2eeff
bump other packages to prevent conflict
geoffreyangus Nov 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 8 additions & 17 deletions server/lorax_server/models/flash_llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

from loguru import logger
from opentelemetry import trace
from transformers.models.llama import LlamaTokenizer, LlamaTokenizerFast
from transformers import AutoTokenizer
from tqdm import tqdm
from typing import Dict, Optional

Expand Down Expand Up @@ -45,22 +45,13 @@ def __init__(
else:
raise NotImplementedError("FlashLlama is only available on GPU")

try:
tokenizer = LlamaTokenizer.from_pretrained(
model_id,
revision=revision,
padding_side="left",
truncation_side="left",
trust_remote_code=trust_remote_code,
)
except Exception:
tokenizer = LlamaTokenizerFast.from_pretrained(
model_id,
revision=revision,
padding_side="left",
truncation_side="left",
trust_remote_code=trust_remote_code,
)
tokenizer = AutoTokenizer.from_pretrained(
model_id,
revision=revision,
padding_side="left",
truncation_side="left",
trust_remote_code=trust_remote_code,
)

config = LlamaConfig.from_pretrained(
model_id, revision=revision, trust_remote_code=trust_remote_code
Expand Down
4 changes: 2 additions & 2 deletions server/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
accelerate==0.19.0 ; python_version >= "3.9" and python_version < "4.0"
accelerate==0.24.1 ; python_version >= "3.9" and python_version < "4.0"
aiohttp==3.8.5 ; python_version >= "3.9" and python_version < "4.0"
aiosignal==1.3.1 ; python_version >= "3.9" and python_version < "4.0"
async-timeout==4.0.2 ; python_version >= "3.9" and python_version < "4.0"
Expand Down Expand Up @@ -62,7 +62,7 @@ texttable==1.6.7 ; python_version >= "3.9" and python_version < "4.0"
tokenizers==0.13.3 ; python_version >= "3.9" and python_version < "4.0"
torch==2.0.1 ; python_version >= "3.9" and python_version < "4.0"
tqdm==4.65.0 ; python_version >= "3.9" and python_version < "4.0"
transformers==4.29.2 ; python_version >= "3.9" and python_version < "4.0"
transformers==4.35.2 ; python_version >= "3.9" and python_version < "4.0"
typer==0.6.1 ; python_version >= "3.9" and python_version < "4.0"
typing-extensions==4.7.1 ; python_version >= "3.9" and python_version < "4.0"
tzdata==2023.3 ; python_version >= "3.9" and python_version < "4.0"
Expand Down
Loading