@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 2832e7b9f9
Fork 0

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