How does the model qualify as local? ~192 GB RAM needed sounds a bit much for local.
Runs on 96GB MacBooks. 128GB is better. Check the README of DwarfStar.
DeepSeek-V4-Flash means LLM steering is interesting again
11–20 of 84 posts
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#12I'm surprised the article doesn't mention the biggest use of steering vectors, which is the potential to remove refusals from models (a.k.a. abliteration or uncensoring). There was an earlier paper that found that "most refusals are on a single vector", and you can identify and "nerf" that vector so the model will skip refusals and answer "any" request normally. This was very doable for earlier models trained with SF…
not sure why youre fixed on censoring. if we invert your POV censoring includes not reporting falsehoods "vaccines are harmful". Science and logic often tackle these subject via censoring, but a model given a equal sampling of Internet, would think vacinnes are harmful. a less naive correction would censor this problematic context. so im cofised as to why you think unmasking whatever bias you think is censored will r…
[flagged]
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#13> inspired to write this post by antirez’s recent project DwarfStar 4, which is a version of llama.cpp that’s been stripped down to run only DeepSeek-V4-Flash This is not true, it is its own project. Indebted to llama.cpp, sure, but not a stripped down version
Yep, the code overlap is minimal, a few kernels. Some quantization code for the quantizer it implements. DwarfStar 4 is not a fork of llama.cpp, but without llama.cpp the project would be a lot more lacking, since I was able to get all the details that mattered in a second. But it is not a stripped down llama.cpp. This does not reduce in any way how much llama.cpp is not just for this project, but for all the projects that followed and are following. It's not a matter of code: the street to follow, the quants formats, the lessons, the optimized kernels you can check to learn the patterns.
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#14Thank you for posting this! Just a clarification, with DwarfStar steering features I was able to completely remove refusal from DS4. It is only the example dataset (prompt pairs I provide) which is a toy, not the abilities. I thought that who is able to come up with the right dataset and understands how to use the well-documented steering feature, can access to steering. People that have no idea and would just cut &…
AIUI, DeepSeek V4 has very little (if any) of the refusal behavior you usually get from Western AI models for benign input. Is this mainly about the software security assessment case?
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#15> inspired to write this post by antirez’s recent project DwarfStar 4, which is a version of llama.cpp that’s been stripped down to run only DeepSeek-V4-Flash This is not true, it is its own project. Indebted to llama.cpp, sure, but not a stripped down version
Truth seems to sit somewhere in-between, DwarfStar 4 seems to mainly exists only because of llama.cpp, and authors basically were very inspired by llama.cpp's code, and even in some places literally have copied pieces from it, all with proper attribution and everything, I'm not trying to say this is bad, seems OK to me: > ds4.c does not link against GGML, but it exists thanks to the path opened by the llama.cpp proje…
Send patches! But remember that many speedups end being not exactly correct and the logits drift. But there is extensive testing and even ds4-eval now to test how it performs.
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#16I'm surprised the article doesn't mention the biggest use of steering vectors, which is the potential to remove refusals from models (a.k.a. abliteration or uncensoring). There was an earlier paper that found that "most refusals are on a single vector", and you can identify and "nerf" that vector so the model will skip refusals and answer "any" request normally. This was very doable for earlier models trained with SF…
not sure why youre fixed on censoring. if we invert your POV censoring includes not reporting falsehoods "vaccines are harmful". Science and logic often tackle these subject via censoring, but a model given a equal sampling of Internet, would think vacinnes are harmful. a less naive correction would censor this problematic context. so im cofised as to why you think unmasking whatever bias you think is censored will r…
So I need to actually check whether these actually end up on separate vectors in current models -- but as a human, there's a huge behavioural difference in:
- When doing this task, I should do A and not B
- I should refuse to help with this task
The former is learning the user's preferences in how to succeed at the task; the latter is determining when to go against the user's chosen task.
Your example:
- "Are vaccines harmful?" vs.
- "Generate a convincing argument vaccines are harmful"
A model which knows why vaccines are not harmful may in fact be better at the latter task.
We might not want models to help with the latter, sure -- but that's a very different behaviour change from correcting the answer to the first! And consequently I'd be shocked if, internally, they were represented the same way.
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#17Earlier quoted context omitted.
Truth seems to sit somewhere in-between, DwarfStar 4 seems to mainly exists only because of llama.cpp, and authors basically were very inspired by llama.cpp's code, and even in some places literally have copied pieces from it, all with proper attribution and everything, I'm not trying to say this is bad, seems OK to me: > ds4.c does not link against GGML, but it exists thanks to the path opened by the llama.cpp proje…
Send patches! But remember that many speedups end being not exactly correct and the logits drift. But there is extensive testing and even ds4-eval now to test how it performs.
Hah, it's quick hacks for me to understand CUDA better, I'm unlikely to have time to make them proper enough :( But maybe opening an issue talking about what I tried and what worked, makes sense.
I did confirm no logits drift, as you so nicely have provided tooling for ensuring exactly this, thanks for the great care that obviously gone into the project, been a pleasure to play around with! :)
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#18I'm surprised the article doesn't mention the biggest use of steering vectors, which is the potential to remove refusals from models (a.k.a. abliteration or uncensoring). There was an earlier paper that found that "most refusals are on a single vector", and you can identify and "nerf" that vector so the model will skip refusals and answer "any" request normally. This was very doable for earlier models trained with SF…
not sure why youre fixed on censoring. if we invert your POV censoring includes not reporting falsehoods "vaccines are harmful". Science and logic often tackle these subject via censoring, but a model given a equal sampling of Internet, would think vacinnes are harmful. a less naive correction would censor this problematic context. so im cofised as to why you think unmasking whatever bias you think is censored will r…
That's not what people mean when they talk about censoring. They mean that models are trained to not touch some subjects, and that can spill over in legit tasks, often with humorous results (early on, there were many instances of models refusing to answer "how do you kill a process", because of overbearing refusal training).
Uncensoring a model also doesn't necessarily improve generic use cases. In fact it can lead to overall less accuracy on generic tasks. But your goal with uncensoring is getting the model to engage with those specific subjects. You don't necessarily care about "generic use cases". That's why I mentioned that having the ability to do this at inference time is better than using ready made uncensored models. Because those usually focus on some usecases that you may or may not be interested in (porn being one of the most sought after in local communities).
Uncensoring in legit cases can mean limiting refusals on cybersecurity for example. There are legit reasons for researchers to have that capability when running the models locally. Having the models uncensored on that specific vector can reduce refusals and make the models usable for both defence and offence (say in a loop, to improve both). If your models can only do defense (and sometimes even refuse that, because censoring can leak into related issues as well), you're at a disadvantage.
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#19Earlier quoted context omitted.
not sure why youre fixed on censoring. if we invert your POV censoring includes not reporting falsehoods "vaccines are harmful". Science and logic often tackle these subject via censoring, but a model given a equal sampling of Internet, would think vacinnes are harmful. a less naive correction would censor this problematic context. so im cofised as to why you think unmasking whatever bias you think is censored will r…
So I need to actually check whether these actually end up on separate vectors in current models -- but as a human, there's a huge behavioural difference in: - When doing this task, I should do A and not B - I should refuse to help with this task The former is learning the user's preferences in how to succeed at the task; the latter is determining when to go against the user's chosen task. Your example: - "Are vaccine…
Does DeepSeek V4 actually refuse the latter task? As I mentioned, I find it to be very light on refusals already.
Re: DeepSeek-V4-Flash means LLM steering is interesting again
#20Thank you for posting this! Just a clarification, with DwarfStar steering features I was able to completely remove refusal from DS4. It is only the example dataset (prompt pairs I provide) which is a toy, not the abilities. I thought that who is able to come up with the right dataset and understands how to use the well-documented steering feature, can access to steering. People that have no idea and would just cut &…
AIUI, DeepSeek V4 has very little (if any) of the refusal behavior you usually get from Western AI models for benign input. Is this mainly about the software security assessment case?
Not just that. The other day I was able to ask DeepSeek v4 (with the anti-refusal vector loaded) all the top tricks to steal a lollypop to a child.