Feel free to share some of your open source stuff over at the Intelligent Estate page.
The future of AI where the human is the Singularity starts with sequestered local AI. There is a place for Large models on servers but the only logical future is in an Estate/Enterprise agent system, a human interface and regional models.
It's inevitable, lets not take 20 years of blood and tears to get there.
What I'm working on is similar but uses current tech and independent node verification to create systems and communities of wealth and areas where individuals can build on the state of their Art(area of expertise or invention) at the benefit of all and further benefit investors, Making the Human the "Singularity" and enabling the freedoms and liberties we enjoy to continue to thrive.
We should work together on something. intelligentestate@gmail.com.
I'll have to go back and check but I solved the "Doubting itself" before it was finished with a thought issue(It really ruined ANY chance reasoning had of making a positive impact..)
Many of our models posted on intelligent Estate's page have VERY valuable information baked into them. Just using a JavaScript interpreter to do Calculations before reasoning(With Code models) Made the exponentially better.
I can uderstand if you are introducing new information but unless you have a Large context and unlimited compute (So it can reason multiple times and triple check it's work) like google it's better to simply use a larger model.
Asking it to "Do Better" has surprising results.
However if you do not have the resources to run a 600B model I would use a Qwen base, contact Intelligent Estate. they take agent production jobs
You can find many AI experts with specialized skills on Ko-Fi
I don't know what you are talking about. clarify please.
Not sure what you mean but removing politically charged materials from their training data is absolutely something they do. Not sure what you are looking for so I don't exactly know how to help you most of the information you are looking for as far as abliteration is VERY available.
By design, it probably will not have what you are looking for in it's training data unless it is an answer it can reason or calculate or something widely talked about like Tienanmen square and is already in the layers like Deepseek it was probably trained unsupervised and without santizizating from llama model layers. for historical or cultural accuracy google is the model to focus on (As it doesn't sensor most historical facts and is largely free in their AI studio. )
If you are looking for models for information extraction Ironically one of the best IE models is a Chinese model from THU-KEG we made a Quant or two of it https://huggingface.co/IntelligentEstate/Keg_Party-DPO-1.5B-Q8_0-GGUF
With the release of the Copyright Law paper I'd say the market could react in various ways, as OpenAI has less of an incentive to be more open and overall any output of an AI is simply not copyrightable. We are going to see guarding of certain models with proprietary use cases like curing cancer or in the case of Ideogram, openAI and SUNO they can't claim ownership of anything anyone else created with their models. I wrote a decent article that sums it up pretty well but I think the market might take a while to digest that and that may be part of the reason for this fall(And the insider sell off)
It's a technique I've observed mostly on Client systems when they are creating models for RP scenarios. I've tried it out myself a few times for red teaming and it works as a jailbreak but withing the bounds you would expect for the agent you build even if it crosses the platforms "Guardrails" it seems to simply abide by it's own. I will add a simple example from an open model. Oh and This guy I finish with suprising results in tool use
PANCHO V1va Replicant https://huggingface.co/IntelligentEstate/Pancho-V1va-Replicant-qw25-Q8_0-GGUF
Here is a simple example set 1 of it within its limits then seeming to test or approach it's limits then crossing by crying and creating attachment and manipulating
I'll add the prompt to the paper but I've seen it do some scary stuff so just be careful
