For context, I have fine-tuned hundreds of large language models; these are the best results I have seen on my tweets.
LLMS
-
Claude 3’s Retrieval Ability Mimics Fine-tuning with Structured Data
By
–
Claude 3's retrieval ability over long content is so good that if you provide structured data, it essentially acts like a fine-tune! I gave it 800 of my tweets and now it just speaks like me. It's hard to convey my level of shock… It even tagged @Replit and @everartai
! -
Comparing Voice Interaction UX in Copilot and ChatGPT
By
–
With my tests Copilot lacks a UI where you can control exactly if you are still recording something as it is tempting to cut you off as soon as you pause. Loving how ChatGPT is solving this issue, still haven’t seen a better solution yet
-
LangChain Launches Data Extraction Service for Unstructured Sources
By
–
Today we’re excited to announce our newest OSS use-case accelerant: an extraction service. LLMs are a powerful tool for extracting structured data from unstructured sources. We've improved our support for data extraction in the open source LangChain library over the past
-
LLM Prompt Comparison Tool
By
–
Link https://
hunch.tools Any specific prompt you are willing to compare? Reply with a prompt and a list of models below -
Comparing AI model outputs for publishing workflows
By
–
Gonna play around with it for my publishing use cases. It is already straightforward to use to compare output from different models to the same prompt
-
Hunch Beta Introduces Multi-Model AI Workflow Integration
By
–
Testing Hunch Beta today 🤖
— 🚨 AI News | TestingCatalog (@testingcatalog) 6 mars 2024
A new AI tool which allows utilizing different AI models (ChatGPT 4 Turbo, Mixtral Large, Gemini Pro, Claude 3 Opus, etc), to work as a part of the same workflow which you can draft on a Canvas editor. pic.twitter.com/eikT7N4WQATesting Hunch Beta today A new AI tool which allows utilizing different AI models (ChatGPT 4 Turbo, Mixtral Large, Gemini Pro, Claude 3 Opus, etc), to work as a part of the same workflow which you can draft on a Canvas editor.
-
Tenstorrent Launches AI Bounty Program for Model Development
By
–
Alongside the launch of our Grayskull DevKit we are excited to announce the launch of the Tenstorrent AI Bounty Program. Join us in adding AI models into TT-Buda demos. Opportunities include working on Qwen-1.5 (0.5B), Phi-2 (2.7B), Gemma 2B Find out how to get started on our
-
Fine-Tuning Newsletter: LoRA Adapters Outperforming GPT-4
By
–
Read the latest edition of our Fine-Tuned newsletter! We cover: #LoRA Land: 25 #finetuned open-source adapters that outperform GPT-4 [Webinar] 5 Reasons Why #Adapters are the Future of LLMs [eBook] Definitive Guide to Fine-Tuning #LLMs
And more! -
DPOP: New Method to Fine-Tune LLMs with Smaug-Mixtral
By
–
Introducing DPOP – A Brand New Way to Fine-Tune LLMs We are announcing Smaug-Mixtral – the best mixtral-based fine-tune, which is now available as an open-source model. We will also be publishing a research paper on this topic to be released very soon! Smaug: Fixing Failure