Greg Schoeninger

Greg Schoeninger

Oct
23
How to run Llama-2 on CPU after fine-tuning with LoRA

How to run Llama-2 on CPU after fine-tuning with LoRA

Running Large Language Models (LLMs) on the edge is a fascinating area of research, and opens up many use cases
10 min read
Oct
20
Arxiv Dives - Generating Speech from Text with Fast Speech-2

Arxiv Dives - Generating Speech from Text with Fast Speech-2

Every Friday at Oxen.ai we host a public paper club called "Arxiv Dives" to make us smarter
11 min read
Oct
13
Arxiv Dives - Llama-2 Explained

Arxiv Dives - Llama-2 Explained

Every Friday at Oxen.ai we host a public paper club called "Arxiv Dives" to make us smarter
10 min read
Oct
09
Arxiv Dives - Stable Diffusion

Arxiv Dives - Stable Diffusion

Every Friday at Oxen.ai we host a public paper club called "Arxiv Dives" to make us smarter
8 min read
Sep
29
Arxiv Dives - How Segment Anything Works

Arxiv Dives - How Segment Anything Works

Every Friday at Oxen.ai we host a public paper club called "Arxiv Dives" to make us smarter
10 min read
Sep
25
Arxiv Dives - Retrieval Augmented Generation (RAG)

Arxiv Dives - Retrieval Augmented Generation (RAG)

Every Friday at Oxen.ai we host a public paper club called "Arxiv Dives" to make us smarter
9 min read
Sep
15
Arxiv Dives - Training Language Models to Follow Instructions (InstructGPT)

Arxiv Dives - Training Language Models to Follow Instructions (InstructGPT)

Join the "Nerd Herd" Every Friday at Oxen.ai we host a public paper club called "Arxiv
8 min read
Sep
08
Arxiv Dives - Language Models are Unsupervised Multitask Learners (GPT-2)

Arxiv Dives - Language Models are Unsupervised Multitask Learners (GPT-2)

Every Friday at Oxen.ai we host a public paper club called "Arxiv Dives" to make us smarter
8 min read
Aug
01
Creating a Cute Custom Character with Stable Diffusion and Dreambooth

Creating a Cute Custom Character with Stable Diffusion and Dreambooth

Introduction Stable Diffusion is an incredible open-source tool for fast, effective generation of novel images across a wide variety of
8 min read
Jul
26
Collecting Data from Human Feedback for Generative AI

Collecting Data from Human Feedback for Generative AI

Human feedback is essential to the accuracy and continual improvement of generative AI systems. Incorporating human ranking of alternative model outputs into model reward functions is a key feature of the training
6 min read