Llama 2
Model ● Covered in 11 stories + Follow
Llama 2 is an open large language model that has been used across a range of implementation and evaluation efforts in recent AI news. Coverage includes deploying Llama 2 via serverless GPU APIs on Cloudflare with Hugging Face, running it on specialized hardware such as Intel Gaudi 2 and AWS Inferentia2, and benchmarking or evaluating models (including Llama 2) for tasks like agent efficiency and hallucination rates. The model has also been referenced in fine-tuning and application contexts, including LoRA-based classification work and frameworks that enable access to large-model inference on non-enterprise hardware.
Updated 17 September 2026
Specifications
No specifications recorded yet.
Latest developments
Petals
petals.dev · 1 month ago ·
37
Is it agentic enough? Benchmarking open models on your own tooling
Hugging Face · 2 months ago ·
6
Welcome Llama 3 - Meta's new open LLM
Hugging Face · 2 years ago ·
17
Bringing serverless GPU inference to Hugging Face users
Hugging Face · 2 years ago ·
5
Text-Generation Pipeline on Intel® Gaudi® 2 AI Accelerator
Hugging Face · 2 years ago ·
16
Introducing Qwen
GitHub Pages · 2 years ago ·
6
A guide to setting up your own Hugging Face leaderboard: an end-to-end example with Vectara's hallucination leaderboard
Hugging Face · 2 years ago ·
38
SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit
Hugging Face · 2 years ago ·
15
Q3 2026
Q2 2026
Q2 2024
Q1 2024
Alibaba Releases Qwen Series of Open-Source Large Language Models and Multimodal Variants Open source release
- Text-Generation Pipeline on Intel® Gaudi® 2 AI Accelerator
- Introducing Qwen
- A guide to setting up your own Hugging Face leaderboard: an end-to-end example with Vectara's hallucination leaderboard
Q4 2023
- SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit
- 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
Q3 2023
Mistral AI releases Mistral 7B open-source language model Open source release
Relationships
Products & technology
- Llama 3 derived from this model · 1 source
- AWS deploys this model · 1 source
- Hugging Face deploys this model · 1 source
- optimum-neuron integrated with this model · 1 source
- Meta develops this model · 1 source
- Intel integrated with this model · 1 source