Search Results for "align"

Hands-On-Large-Language-Models is the official GitHub code repository accompanying the practical technical book Hands-On Large Language Models authored by Jay Alammar and Maarten Grootendorst, providing a comprehensive collection of example notebooks, code labs, and supporting materials that illustrate the core concepts and real-world applications of large language models. The repository is structured into chapters that align with the educational progression of the book — covering everything from foundational topics like tokens, embeddings, and transformer architecture to advanced techniques such as prompt engineering, semantic search, retrieval-augmented generation (RAG), multimodal LLMs, and fine-tuning. Each chapter contains executable Jupyter notebooks that are designed to be run in environments like Google Colab, making it easy for learners to experiment interactively with models, visualize attention patterns, implement classification and generation tasks.

...Traditional automatic speech recognition systems can misinterpret these sounds as words, leading to inaccurate transcripts. WhisperJAV introduces a specialized pipeline that separates text generation from timestamp alignment, allowing the system to generate transcripts and then align them with audio using forced alignment techniques. The framework supports several speech recognition models, including Qwen-based ASR systems and fine-tuned Whisper models trained on domain-specific dialogue.

MedicalGPT training medical GPT model with ChatGPT training pipeline, implementation of Pretraining, Supervised Finetuning, Reward Modeling and Reinforcement Learning. MedicalGPT trains large medical models, including secondary pre-training, supervised fine-tuning, reward modeling, and reinforcement learning training.

...Its reasoning capabilities have been strengthened, including improved tool usage during inference and more effective integration within agent frameworks. GLM-4.6 also enhances writing quality, producing outputs that better align with human preferences and role-playing scenarios. Benchmark evaluations demonstrate that it not only outperforms GLM-4.5 but also rivals leading global models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4.

The Alignment Handbook is an open-source resource created to provide practical guidance for aligning large language models with human preferences and safety requirements. The project focuses on the post-training stage of model development, where models are refined after pre-training to behave more helpfully, safely, and reliably in real-world applications. It provides detailed training recipes that explain how to perform tasks such as supervised fine-tuning, preference modeling, and...

Qwen2.5-Omni is an end-to-end multimodal flagship model in the Qwen series by Alibaba Cloud, designed to process multiple modalities (text, images, audio, video) and generate responses both as text and natural speech in streaming real-time. It supports “Thinker-Talker” architecture, and introduces innovations for aligning modalities over time (for example synchronizing video/audio), robust speech generation, and low-VRAM/quantized versions to make usage more accessible. It holds...

...The project focuses primarily on safety testing scenarios relevant to Chinese language models, though the concepts can be applied to other languages and systems. The prompts are structured to test whether models generate outputs that align with human values and safety guidelines when faced with potentially harmful or sensitive requests. Researchers and developers use the dataset to benchmark how well models avoid unsafe responses and follow alignment constraints. The repository also serves as a training resource for improving model alignment by providing examples of prompts that require safe reasoning and appropriate refusal behavior. ...

lm-human-preferences is the official OpenAI codebase that implements the method from the paper Fine-Tuning Language Models from Human Preferences. Its purpose is to show how to align language models with human judgments by training a reward model from human comparisons and then fine-tuning a policy model using that reward signal. The repository includes scripts to train the reward model (learning to rank or score pairs of outputs), and to fine-tune a policy (a language model) with reinforcement learning (or related techniques) guided by that reward model. ...