Picture for Guoyang Zeng

Guoyang Zeng

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Add code
Aug 03, 2024
Viaarxiv icon

PyBench: Evaluating LLM Agent on various real-world coding tasks

Add code
Jul 23, 2024
Figure 1 for PyBench: Evaluating LLM Agent on various real-world coding tasks
Figure 2 for PyBench: Evaluating LLM Agent on various real-world coding tasks
Figure 3 for PyBench: Evaluating LLM Agent on various real-world coding tasks
Figure 4 for PyBench: Evaluating LLM Agent on various real-world coding tasks
Viaarxiv icon

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Add code
Apr 09, 2024
Figure 1 for MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Figure 2 for MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Figure 3 for MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Figure 4 for MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Viaarxiv icon

D-Bot: Database Diagnosis System using Large Language Models

Add code
Dec 06, 2023
Viaarxiv icon

Unlock Predictable Scaling from Emergent Abilities

Add code
Oct 05, 2023
Viaarxiv icon

QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation

Add code
Sep 20, 2023
Viaarxiv icon

CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark

Add code
Dec 27, 2021
Figure 1 for CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
Figure 2 for CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
Figure 3 for CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
Figure 4 for CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
Viaarxiv icon

CPM-2: Large-scale Cost-effective Pre-trained Language Models

Add code
Jun 24, 2021
Figure 1 for CPM-2: Large-scale Cost-effective Pre-trained Language Models
Figure 2 for CPM-2: Large-scale Cost-effective Pre-trained Language Models
Figure 3 for CPM-2: Large-scale Cost-effective Pre-trained Language Models
Figure 4 for CPM-2: Large-scale Cost-effective Pre-trained Language Models
Viaarxiv icon

CPM: A Large-scale Generative Chinese Pre-trained Language Model

Add code
Dec 01, 2020
Figure 1 for CPM: A Large-scale Generative Chinese Pre-trained Language Model
Figure 2 for CPM: A Large-scale Generative Chinese Pre-trained Language Model
Figure 3 for CPM: A Large-scale Generative Chinese Pre-trained Language Model
Figure 4 for CPM: A Large-scale Generative Chinese Pre-trained Language Model
Viaarxiv icon

OpenAttack: An Open-source Textual Adversarial Attack Toolkit

Add code
Sep 19, 2020
Figure 1 for OpenAttack: An Open-source Textual Adversarial Attack Toolkit
Figure 2 for OpenAttack: An Open-source Textual Adversarial Attack Toolkit
Figure 3 for OpenAttack: An Open-source Textual Adversarial Attack Toolkit
Figure 4 for OpenAttack: An Open-source Textual Adversarial Attack Toolkit
Viaarxiv icon