EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[CI]Add model basic accuracy test(Qwen2.5-0.5B-Instruct) (#460)

Browse Source 
### What this PR does / why we need it?
Add model basic accuracy test(Qwen2.5-0.5B-Instruct)

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
hfadzxy
2025-04-17 14:59:56 +08:00
committed by GitHub
parent c3d1a3782a
commit 9935d45728
49 changed files with 145 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm_ascend/models/deepseek_v2.py
View File

@@ -1,9 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# Adapted from
# vllm-project/vllm/blob/main/vllm/model_executor/models/deepseek_v2.py
# https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py
# vllm-project/vllm/vllm/model_executor/models/deepseek_v2.py
# Copyright 2023 The vLLM team.
# Copyright 2023 DeepSeek-AI and the HuggingFace Inc. team. All rights reserved.
#
@@ -23,6 +19,10 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Adapted from
# vllm-project/vllm/blob/main/vllm/model_executor/models/deepseek_v2.py
# https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py
# vllm-project/vllm/vllm/model_executor/models/deepseek_v2.py
"""Inference-only DeepseekV2/DeepseekV3 model."""
from typing import Optional, Union