![Brev](/img/default-banner.jpg)
- 17
- 134 050
Brev
United States
เข้าร่วมเมื่อ 26 เม.ย. 2021
Easy-to-use GPUs
How do LLM Inference Optimizations Work? NVIDIA Coffee Chat
How do LLM inference Optimizations Work? Nader (Director of Dev Tech at NVIDIA) had this question so he sat down with the legend, Kyle Kranen to learn more about them. NVIDIA is full of experts on anything AI related, is there something you want to learn about?
มุมมอง: 276
วีดีโอ
Fine-Tune Llama 3.1 and Deploy Using NVIDIA NIM Directly From Your Laptop
มุมมอง 16Kหลายเดือนก่อน
NVIDIA Developer Program: developer.nvidia.com/nim Get Access To The NIM: build.nvidia.com/meta/llama-3_1-8b-instruct Follow Along: brev.dev/llama3-1-nim In this tutorial, we walk through getting access to the NVIDIA Developer program to gain access to the cutting edge Llama3.1 8B Instruct Model NIM. We fine-tune Llama 3.1 using a PEFT technique called LoRA using the NVIDIA Nemo Framework. And ...
Fine-Tune Any LLM, Convert to GGUF, And Deploy Using Ollama
มุมมอง 3.3K2 หลายเดือนก่อน
Follow Along: console.brev.dev/launchable/deploy/now?userID=p2mzt91a8&orgID=ejmrvoj8m&name=Finetune Llama3 and Convert to Ollama Modelfile&instance=A10G@g5.2xlarge&diskStorage=500&cloudID=devplane-brev-1&python=3.10&cuda=12.0.1&file=https://github.com/brevdev/notebooks/blob/main/llama3-to-ollama.ipynb&launchableID=env-2iBAoNimbkT4imNoAQXyIOXwrXd Join Our Discord: discord.com/invite/NVDyv7TUgJ R...
How to Run Stable-Diffusion using TensorRT and ComfyUI
มุมมอง 3.6K2 หลายเดือนก่อน
Follow Along: console.brev.dev/launchable/deploy/now?userID=xswf1irzo&orgID=ejmrvoj8m&name=comfyUI-tensorRT-carter&instance=RTX A6000@NVIDIA-RTX A6000-48Gi-PCIe-1x&diskStorage=500&cloudID=akash-brev-wg&baseImage=nvcr.io/nvidia/tensorrt:24.05-py3&ports=comfyui:8188&file=https://github.com/brevdev/notebooks/blob/main/tensorrt-comfyui.ipynb&launchableID=env-2hU1R3hVyeFKQVnrmS8KPUiAUe2 Join Our Dis...
How To FineTune Llama3
มุมมอง 9K3 หลายเดือนก่อน
Follow Along: console.brev.dev/launchable/deploy/now?userID=p2mzt91a8&orgID=jnj0c501d&name=Fine-tune Llama3 using Direct Preference Optimization&instance=A100@a100.1x&cloudID=crusoe-brev-wg&python=3.10&cuda=12.0.1&file=https://github.com/brevdev/notebooks/blob/main/llama3dpo.ipynb&launchableID=env-2hRHIhATRIw8sCD6QwT11eYn6Vf Join Our Discord: discord.com/invite/NVDyv7TUgJ Request Access To the ...
How To Fine-tune LLaVA Model (From Your Laptop!)
มุมมอง 12K4 หลายเดือนก่อน
Follow Along: console.brev.dev/launchable/deploy/now?userID=p2mzt91a8&orgID=jnj0c501d&launchableID=env-2hpxJ6HArVk5jzOYgJmFDJfvNmH&instance=A10G@g5.12xlarge&diskStorage=300&cloudID=devplane-brev-1&python=3.10&cuda=12.2.2&file=https://github.com/brevdev/notebooks/blob/main/llava-finetune.ipynb&name=Fine-tune and deploy multimodal LLaVA-1.5 Join Our Discord: discord.com/invite/NVDyv7TUgJ In this ...
How to Fine-tune Mixtral 8x7B MoE on Your Own Dataset
มุมมอง 2.6K7 หลายเดือนก่อน
In this video, we show you how to fine-tune Mixtral, Mistral's 8x7B MoE (Mixture of Experts) model, on your own dataset. You'll be directed to another video where we fine-tune Mistral 7B (standard Mistral) on your own dataset, but you'll be using the notebook here: github.com/brevdev/notebooks/blob/main/mixtral-finetune-own-data.ipynb My explanation on how QLoRA works: brev.dev/blog/how-qlora-w...
Chat with your PDFs with Open Source OCR (Optical Character Recognition) & Mistral Lite
มุมมอง 2.5K7 หลายเดือนก่อน
Hi there! Harper Carroll from Brev.dev here. In this tutorial, we go through a pre-made Jupyter Notebook to run OCR (Optical Character Recognition) on our uploaded PDFs to extract the text, and then we use Amazon's MistralLite to ask questions about those PDFs. Amazon's MistralLite is its fine-tuned version of Mistral 7B, which allows for context lengths of up to 32K tokens... this means we can...
Generate AI Images with the Stable Diffusion Web UI AUTOMATIC1111 - No Code Tutorial
มุมมอง 8567 หลายเดือนก่อน
Hi! Harper Carroll from Brev.dev here. In this video, we walk through how to run the most popular open source Stable Diffusion Web UI, AUTOMATIC1111. No coding of your own needed. Just plug & play. Notebook: github.com/brevdev/notebooks/blob/main/automatic1111-stable-diffusion-ui.ipynb Other AI/ML Notebooks: github.com/brevdev/notebooks Find me on 𝕏: x.com/HarperSCarroll/highlights Join our Dis...
How to Fine-Tune Llama 2 (on your own data or on a HF dataset) - Video Walkthrough
มุมมอง 1.7K7 หลายเดือนก่อน
Fine-tune on your own dataset notebook: github.com/brevdev/notebooks/blob/main/llama2-finetune-own-data.ipynb Video: th-cam.com/video/kmkcNVvEz-k/w-d-xo.html Fine-tune on a HuggingFace dataset notebook: github.com/brevdev/notebooks/blob/main/llama2-finetune.ipynb Video: th-cam.com/video/zbKz4g100SQ/w-d-xo.html Other AI/ML Notebooks: github.com/brevdev/notebooks Find me on 𝕏: x.com/HarperSCarrol...
How to Fine-tune Phi-2 - Video Walkthrough
มุมมอง 3K7 หลายเดือนก่อน
Fine-tune on your own dataset notebook: github.com/brevdev/notebooks/blob/main/phi2-finetune-own-data.ipynb Video: th-cam.com/video/kmkcNVvEz-k/w-d-xo.html Fine-tune on a HuggingFace dataset notebook: github.com/brevdev/notebooks/blob/main/phi2-finetune.ipynb Video: th-cam.com/video/zbKz4g100SQ/w-d-xo.html Other AI/ML Notebooks: github.com/brevdev/notebooks Find me on 𝕏: x.com/HarperSCarroll/hi...
Fine-Tune Mixtral 8x7B (Mistral's Mixture of Experts MoE) Model - Walkthrough Guide
มุมมอง 15K8 หลายเดือนก่อน
Hi! Harper Carroll from Brev.dev here. In this tutorial video, I walk you through how to fine-tune Mixtral, Mistral’s 8x7B Mixture of Experts (MoE) model, which outperforms Llama 2 70B on most tested benchmarks. Thanks everyone for 1K subscribers! So glad these are helpful. You rock. Notebook: github.com/brevdev/notebooks/blob/main/mixtral-finetune.ipynb My explanation on how QLoRA works: brev....
OpenAI's Q*?: Reinforcement Learning, Model-Based vs. Model-Free Methods, and Q-Learning
มุมมอง 1.5K9 หลายเดือนก่อน
In this Brev.dev Concepts video, Harper Carroll (Head of AI/ML) covers the basics of reinforcement learning, exploration and exploitation, model-based vs. model-free methods, Q-learning, Q*, and temporal difference learning. It is accessible to those of all backgrounds, and includes a little math for those interested. Find me on 𝕏: HarperSCarroll Join our community on Discord: disco...
How to Fine-Tune Mistral 7B on Your Own Data
มุมมอง 60K10 หลายเดือนก่อน
Hi! Harper Carroll from Brev.dev here. In this tutorial video, I walk you through how to fine-tune Mistral 7B, which outperforms Llama 2 13B on all tested benchmarks, on your own data.... like how I do with my journal entries from over the years, teen angst and all. Notebook: github.com/brevdev/notebooks/blob/main/mistral-finetune-own-data.ipynb Notebook to fine-tune on a HF dataset: github.com...
How to easily use LoRAs on the Stable Diffusion AUTOMATIC1111 UI
มุมมอง 709ปีที่แล้ว
Want to create Stable Diffusion images that are as stunning as Midjourney's? Let's use LoRAs (low rank adaptation models) to create stunning Stable Diffusion models in our styles of choice! Link to the template & pre-set GPU: github.com/brevdev/AUTOMATIC1111-civitai-notebook (NVIDIA A10G - $1.21 per hour running; you can select a different machine in "Hardware" if you'd like to downgrade). Link...
Setup and Run Dreambooth in 5 Minutes for free
มุมมอง 853ปีที่แล้ว
Setup and Run Dreambooth in 5 Minutes for free
Build a fully deployed React app with Brev
มุมมอง 1.3K3 ปีที่แล้ว
Build a fully deployed React app with Brev