TLDRocket
Sign in

Natural Language Processing

6 summarised stories about Natural Language Processing, each linking back to the original source. Browse all topics →

Tuesday, 7 November 2023

Comparing the Performance of LLMs: A Deep Dive into Roberta, Llama 2, and Mistral for Disaster Tweets Analysis with Lora

Hugging Face Blog 2 years ago

Researchers compared three language models—RoBERTa, Llama 2, and Mistral 7B—fine-tuned with LoRA (Low-Rank Adaptation) for classifying disaster-related tweets. The study used 7,613 training tweets split into train (6,090), validation (1,523), and test (3,263) samples, with class weights of 1.16 for positive and 0.88 for negative examples to address imbalance. Fine-tuning was performed with LoRA to reduce trainable parameters while maintaining performance on the sequence classification task.

Introducing Prodigy-HF: a direct integration with Hugging Face

Hugging Face Blog 2 years ago

Explosion released Prodigy-HF, a plugin that integrates its Prodigy annotation tool directly with Hugging Face models and infrastructure. Users can now fine-tune transformer models like distilbert-base-uncased on annotated data with a single command and upload datasets to the Hugging Face Hub via the hf.upload recipe. This enables faster iteration on domain-specific NLP tasks by allowing models trained on annotated data to be reused for further annotation work.