A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 05:30 UTC
fix names and license for Qwen2 (#2589)
Junyang Lin committed
Jan 25, 2024 at 14:37 UTC
2832e7b9f92e2d1dd7dfe37951e5837c61d3db20
2 files changed
+4
-3
docs/source/models/supported_models.rst
+1
-1
@@ -70,7 +70,7 @@ Alongside each architecture, we include some popular models that use it.
70
- :code:`Qwen/Qwen-7B`, :code:`Qwen/Qwen-7B-Chat`, etc.
71
* - :code:`Qwen2ForCausalLM`
72
- Qwen2
73
- - :code:`Qwen/Qwen2-7B-beta`, :code:`Qwen/Qwen-7B-Chat-beta`, etc.
73
+ - :code:`Qwen/Qwen2-beta-7B`, :code:`Qwen/Qwen2-beta-7B-Chat`, etc.
74
* - :code:`StableLMEpochForCausalLM`
75
- StableLM
76
- :code:`stabilityai/stablelm-3b-4e1t/` , :code:`stabilityai/stablelm-base-alpha-7b-v2`, etc.
vllm/model_executor/models/qwen2.py
+3
-2
@@ -1,7 +1,8 @@
1
# coding=utf-8
2
# Adapted from
3
# https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/qwen2/modeling_qwen2.py
4
-# Copyright 2024 The Qwen team and the HuggingFace Inc. team.
4
+# Copyright 2024 The Qwen team.
5
+# Copyright 2023 The vLLM team.
6
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
7
#
8
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
@@ -20,7 +21,7 @@
21
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
22
# See the License for the specific language governing permissions and
23
# limitations under the License.
23
-"""Inference-only Mistral model compatible with HuggingFace weights."""
24
+"""Inference-only Qwen2 model compatible with HuggingFace weights."""
25
from typing import List, Optional, Tuple
26
27
import torch