Llama-3.1-8B-Instruct news

Six Llamas: Comparative Religious Ethics Through LoRA-Adapted Language Models

arXiv:2604.18404v1 Announce Type: new Abstract: We present Six Llamas, a comparative study examining whether large language models fine-tuned on distinct religious corpora encode systematically different patterns of ethical reasoning. Six variants of Meta-Llama-3.1-8B are constructed: one unmodified

Benchmarking Linguistic Adaptation in Comparable-Sized LLMs: A Study of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali

arXiv:2604.14171v1 Announce Type: new Abstract: Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digital communication in Nepal, yet it remains critically underresourced in the landscape of Large Language Models (LLMs). This study presents a sy

Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference

arXiv:2604.12168v1 Announce Type: cross Abstract: The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance, transportation, and information security, have led to significant improvements in service efficiency and low

Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models

arXiv:2604.10985v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, the

SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration

arXiv:2409.02231v5 Announce Type: replace-cross Abstract: We show that large language model (LLMs) can be transformed via supervised fine-tuning (SFT) of engineered prompts into SmileyLlama for exploring the chemical space of drug molecules. We benchmark SmileyLlama against pre-trained LLMs and chem

Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA

arXiv:2512.12812v2 Announce Type: replace-cross Abstract: Prompt engineering has emerged as a critical factor influencing large language model (LLM) performance, yet the impact of pragmatic elements such as linguistic tone and politeness remains underexplored, particularly across different model fam

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

New in llama.cpp: Model Management

Measuring Open-Source Llama Nemotron Models on DeepResearch Bench

Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub

Welcoming Llama Guard 4 on Hugging Face Hub

Welcome Llama 4 Maverick & Scout on Hugging Face

Welcome Llama 4 Maverick & Scout on Hugging Face

“Llama 3.2 in Keras”

Llama can now see and run on your device - welcome Llama 3.2

Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Welcome Llama 3 - Meta's new open LLM

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

Make your llama generation time fly with AWS Inferentia2

Non-engineers guide: Train a LLaMA 2 chatbot

Llama 2 on Amazon SageMaker a Benchmark

Fine-tuning Llama 2 70B using PyTorch FSDP

Code Llama: Llama 2 learns to code

Fine-tune Llama 2 with DPO

Llama 2 is here - get it on Hugging Face

StackLLaMA: A hands-on guide to train LLaMA with RLHF

Can Large Language Models Reliably Extract Physiology Index Values from Coronary Angiography Reports?

arXiv:2604.13077v1 Announce Type: new Abstract: Coronary angiography (CAG) reports contain clinically relevant physiological measurements, yet this information is typically in the form of unstructured natural language, limiting its use in research. We investigate the use of Large Language Models (LL

SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization

arXiv:2604.07663v1 Announce Type: new Abstract: The AdamW optimizer, while standard for LLM pretraining, is a critical memory bottleneck, consuming optimizer states equivalent to twice the model's size. Although light-state optimizers like SinkGD attempt to address this issue, we identify the embedd

The Last Fingerprint: How Markdown Training Shapes LLM Prose

arXiv:2603.27006v1 Announce Type: cross Abstract: Large language models produce em dashes at varying rates, and the observation that some models "overuse" them has become one of the most widely discussed markers of AI-generated text. Yet no mechanistic account of this pattern exists, and the paralle