73 lines
2.8 KiB
Markdown
73 lines
2.8 KiB
Markdown
---
|
||
license: mit
|
||
# language:
|
||
# - zh
|
||
# metrics:
|
||
# - accuracy
|
||
# base_model:
|
||
# - deepseek-ai/DeepSeek-V3
|
||
# - deepseek-ai/DeepSeek-V3-Base
|
||
# base_model_relation: merge
|
||
library_name: transformers
|
||
# pipeline_tag: image-text-to-text
|
||
# widget:
|
||
# - src: >-
|
||
# https://huggingface.co/iSolver-AI/FEnet/resolve/main/xiaohongshu-girls-enndme-1.jpg
|
||
# example_title: enndme-pic-1
|
||
# output:
|
||
# text: Hello my name is Julien
|
||
# - src: >-
|
||
# https://huggingface.co/iSolver-AI/FEnet/resolve/main/xiaohongshu-girls-enndme-2.jpg
|
||
# example_title: enndme-pic-2
|
||
# output:
|
||
# - label: POSITIVE
|
||
# score: 0.8
|
||
# - src: >-
|
||
# https://huggingface.co/iSolver-AI/FEnet/resolve/main/xiaohongshu-girls-enndme-3.jpg
|
||
# example_title: enndme-pic-3
|
||
# output:
|
||
# - label: POSITIVE
|
||
# score: 0.8
|
||
# tags:
|
||
# - mlx
|
||
# - llama
|
||
# - llama3
|
||
# - transformers
|
||
# - Reward Model
|
||
# - conversational
|
||
|
||
---
|
||
|
||
test webhook
|
||
|
||
# Paper:
|
||
- ✅来源于HF+arxiv，完整输入HF链接的论文：[F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://huggingface.co/papers/2410.06885)
|
||
- ✅来源于HF+arxiv，完整输入arxiv链接的论文：https://arxiv.org/abs/2410.11817
|
||
- 来源于HF+arxiv，仅输入标题+编号的论文：[Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction](2409.18124)
|
||
- 来源于HF+arxiv，仅输入标题的论文：Exploring Model Kinship for Merging Large Language Models
|
||
- ✅来源于HF+arxiv，输入「arxiv:编号」的论文：arxiv:2410.12381
|
||
- ✅来源于HF+arxiv，输入链接不带https://前缀：arxiv.org/abs/2410.09401
|
||
|
||
- ✅仅来源于arxiv，完整输入arxiv链接的论文：[Improving Prototypical Parts Abstraction for Case-Based Reasoning Explanations Designed for the Kidney Stone Type Recognition](https://arxiv.org/abs/2409.12883)，因为有READme引用而自动导入该paper到Daily Paper,变成arxiv和HF都有的论文
|
||
- ✅仅来源于arxiv，完整输入arxiv链接的论文：[Aharonov-Bohm effects on the GUP framework](https://arxiv.org/abs/2410.11888)，会因为有READme引用而自动导入该paper到Daily Paper
|
||
- 仅来源于arxiv，仅输入编号的论文：2409.00821
|
||
- 仅来源于arxiv，仅输入标题的论文：An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentation
|
||
|
||
- 非arxiv论文：
|
||
@inproceedings{DBLP:conf/nips/XuLCLQ21,
|
||
author={Yong Xu and Feng Li and Zhile Chen and Jinxiu Liang and Yuhui Quan},
|
||
title={Encoding Spatial Distribution of Convolutional Features for Texture Representation},
|
||
year={2021},
|
||
cdate={1609459200000},
|
||
pages={22732-22744},
|
||
url={https://proceedings.neurips.cc/paper/2021/hash/c04c19c2c2474dbf5f7ac4372c5b9af1-Abstract.html},
|
||
booktitle={NeurIPS},
|
||
crossref={conf/nips/2021}
|
||
}
|
||
|
||
|
||
> 数据集标题record：allenai/WildBench
|
||
|
||
> 模型标题record：==black-forest-labs/FLUX.1-dev==
|
||
|
||
> 数据集标题record：LLM360/TxT360 sasad |