With the recent update to OpenAI's Terms of Use on October 23, 2024, there’s been a flurry of online discussions around what these terms mean for developers, businesses, and everyday users of AI tools like ChatGPT. Much of the conversation, especiall...| Cognitive Computations
Gratitude to https://tensorwave.com/ for giving me access to their excellent servers! Few have tried this and fewer have succeeded. I've been marginally successful after a significant amount of effort, so it deserves a blog post. Know that you are in...| Cognitive Computations
https://huggingface.co/cognitivecomputations/dolphin-2.6-mixtral-8x7b Please Note, that this model is uncensored, and will answer any questions you put to it. You are the sole author of any content that you generate with it. Enjoy responsibly. Do not...| Cognitive Computations
I started to understand that a lot of people are using and enjoying Dolphin - so I decided to put a list here of products or projects that use Dolphin. If you would like to be listed here please reach out to me and I'll add you! HopeBot https://disbo...| Cognitive Computations
Wanna chat with Dolphin locally? (no internet connection needed) Here is the easy way - Ollama. install ollama. after you finsh you should be able to run ollama from the command line. Also you will see the ollama icon up top like this: Iff you ar...| Cognitive Computations
Today I am announcing Dolphin, an open-source and uncensored, and commercially licensed dataset and series of instruct-tuned language models based on Microsoft's Orca paper. The dataset is released here, with Apache-2.0 license. The dataset can be us...| Cognitive Computations
https://huggingface.co/ehartford/based-30b So, as I was working on Wizard-Vicuna-30b-Uncensored and WizardLM-Uncensored-Falcon-7b, I came to the realization that these models, despite being trained with no refusals, were still refusing. How could thi...| Cognitive Computations
https://huggingface.co/ehartford/Samantha-1.11-70b https://huggingface.co/ehartford/samantha-7b https://huggingface.co/ehartford/samantha-13b https://huggingface.co/ehartford/samantha-33b https://huggingface.co/ehartford/samantha-falcon-7b https://hu...| Cognitive Computations
I asked GPT-4 to respond to my previous article "Uncensored Models" because it is more likely to provide civil discourse rather than the shrill demagoguery that my human opponents have tended to employ. I found it interesting and both sides have vali...| Cognitive Computations
A new LLaMA-derived model has appeared, called Vicuna. Now I've been playing with a lot of models like this, such as Alpaca and GPT4All. And I also fine-tuned my own. But Vicuna is a lot better. Here is a conversation I had with it. User: Write a lim...| Cognitive Computations
At first there was Open-Assistant, then appeared OpenChatKit, and the newly announced ColossalChat. Now three projects (that I know of!) aim to give everybody the ability to create their own ChatGPT clone. The basic components of a ChatGPT clone are:...| Cognitive Computations
I thought I would try out ChatGPT's new API, so I decided to write a command line interface. My code is located here: I wanted it to be conversational, so it will remember your conversation history as you type. Similar to chatgpt-wrapper. https://gi...| Cognitive Computations
It's been a while. And I'm digging into Machine Learning. I was watching the excellent video by Andrej Karpathy about how to write a GPT (of which GPT-3 is an example) from scratch, using the paper "Attention is all you need" I implemented it from s...| Cognitive Computations
So I wanted to upload CSV to DynamoDB.Easy right?Not so fast. It turns out, you have to obey your provisioned write capacity. Unlike S3, "Simple Storage Service" where you simply upload a file, DynamoDB isn't "Simple". There's no "upload CSV" bu...| Cognitive Computations
When a16z generously sponsored Dolphin, I had some compute budget, and because the original dolphin-13b was a flop, I had some time to go back to the drawing board. When I was ready to train the next iteration, I reconsidered whether to rent or buy t...| Cognitive Computations
I want to write about fine-tuning Alpaca 30b 4-bit on consumer hardware, but before I can, I'll need to give a little background. My basic goal was to figure out "what's the most powerful AI I can customize and run on my shiny new 4090." The answer r...| Cognitive Computations
I am publishing this because many people are asking me how I did it, so I will explain. https://huggingface.co/ehartford/WizardLM-30B-Uncensored https://huggingface.co/ehartford/WizardLM-13B-Uncensored https://huggingface.co/ehartford/WizardLM-7B-Unc...| Cognitive Computations
