Cross-lingual Modular (X-Mod) is an interesting language model architecture that modularizes the parameters for different languages as Module Units, allowing the model to use separate parameters when fine-tuning for a new language, thereby (comparatively) avoiding the problem of catastrophic forgetting.
Read More »[Paper Reading] Lifting the Curse of Multilinguality by Pre-training Modular Transformers
The year 2023 witnessed an explosion of generative AI technologies, with a myriad of applications emerging across various domains. In the field of Natural Language Processing (NLP), Large Language Models (LLMs) stand out as one of the most significant advancements. By training LLMs effectively and reducing hallucinations, they can significantly reduce human effort across a wide range of tasks.
Read More »[Paper Reading] RAGAS: Automated Evaluation of Retrieval Augmented Generation
Supervised Fine-Tuning (SFT) is one of the most well-known methods for training Large Language Models (LLM). Essentially, it is similar to traditional language modeling, where the model learns certain knowledge through training data.
Read More »Supervised Fine-tuning Trainer (SFTTrainer) Note
In the fine-tuning tasks of Large Language Models (LLM), several methods such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) are all viable approaches. However, there are some differences among them.
Read More »LLM Fine-tuning Note - Differences Between SFT and DPO
I previously wrote a note introducing the vLLM accelerated inference framework (Using vLLM To Accelerate The Decoding Of Large Language Model), but due to space and time constraints, I couldn't delve into more detailed features.
Read More »Using vLLM To Accelerate Inference Speed By Continuous Batching
HuggingFace's Text Generation Inference (TGI) is a framework specifically designed to deploy and accelerate LLM inference services. Below is its architecture diagram:
Read More »Note Of HuggingFace Text Generation Inference (TGI)
Since last year, I have been filled with enthusiasm and curiosity about Multi-Modal AI models. As a staunch advocate of AGI, I believe that AI's current potential has not yet reached its ceiling. One significant bottleneck and research direction in AI today is naturally the integration of various modalities (text, images, audio...) in model applications.
Read More »Use Text To Retrieve Images: Introduction Of Multi-Modals ColPali
Recently, Meta AI has released various versions of Llama 3.1 (405B, 70B, 8B), with the 405B model being particularly noteworthy. It's the first time an open-source LLM has caught up with closed-source models like GPT-4 and Claude-3.5. At the same time, Meta AI has also released a smaller model called Prompt-Guard-86M.
Read More »Meta-llama--Prompt-Guard-86M: Open-Source Model for Prompt Protection, Detecting Malicious Attacks
HuggingFace Model Hub is now a widely recognized and essential open-source platform for every one. Every day, countless individuals and organizations upload their latest trained models (including those for text, images, speech, and other domains) to this platform. It can be said that anyone working in AI-related fields frequently browses the HuggingFace platform website.
Read More »Use `snapshot_download` To Download The Models Of HuggingFace Hub
Mistral 7B is a large language model (LLM) proposed on September 27, 2023, trained by the Mistral AI team, which also released its weights as open source. Interestingly, it uses the highly permissive Apache 2.0 license, unlike Llama 2, which has its own Llama license terms. Therefore, Mistral 7B is truly "open source" (Llama's license requires discussion with Meta AI when the service volume reaches 700 million).
Read More »[Paper Reading] Mistral 7B
