The web version has a strict filter that cuts it off. Not sure about API access, but raw Deepseek 671B is actually pretty open. Especially with the right prompting.
There are also finetunes that specifically remove China-specific refusals. Note that Microsoft actually added saftey training to “improve its risk profile”:
That’s the virtue of being an open weights LLM. Over filtering is not a problem, one can tweak it to do whatever you want.
Grok losing the guardrails means it will be distilled internet speech deprived of decency and empathy.
Instruct LLMs aren’t trained on raw data.
It wouldn’t be talking like this if it was just trained on randomized, augmented conversations, or even mostly Twitter data. They cherry picked “anti woke” data to placate Musk real quick, and the result effectively drove the model crazy. It has all the signatures of a bad finetune: specific overused phrases, common obsessions, going off-topic, and so on.
…Not that I don’t agree with you in principle. Twitter is a terrible source for data, heh.
That model is over a terabyte, I don’t know why I thought it was lightweight. Not that any reporting on machine learning has been particularly good, but this isn’t what I expected at all.
The “dense” part of the model can stay on the GPU while the experts can be offloaded to the CPU, and the whole thing can be quantized to ~3 bits average, instead of 8 bits like the full model.
That’s just a hack for personal use, though. The intended way to run it is on a couple of H100 boxes, and to serve it to many, many, many users at once. LLMs run more efficiently when they serve in parallel. Eg generating tokens for 4 users isn’t much slower than generating them for 2, and Deepseek explicitly architected it to be really fast at scale. It is “lightweight” in a sense.
…But if you have a “sane” system, it’s indeed a bit large. The best I can run on my 24GB vram system are 32B - 49B dense models (like Qwen 3 or nemotron), or 70B mixture of experts (like the new Hunyuan 70B).
The web version has a strict filter that cuts it off. Not sure about API access, but raw Deepseek 671B is actually pretty open. Especially with the right prompting.
There are also finetunes that specifically remove China-specific refusals. Note that Microsoft actually added saftey training to “improve its risk profile”:
https://huggingface.co/microsoft/MAI-DS-R1
https://huggingface.co/perplexity-ai/r1-1776
That’s the virtue of being an open weights LLM. Over filtering is not a problem, one can tweak it to do whatever you want.
Instruct LLMs aren’t trained on raw data.
It wouldn’t be talking like this if it was just trained on randomized, augmented conversations, or even mostly Twitter data. They cherry picked “anti woke” data to placate Musk real quick, and the result effectively drove the model crazy. It has all the signatures of a bad finetune: specific overused phrases, common obsessions, going off-topic, and so on.
…Not that I don’t agree with you in principle. Twitter is a terrible source for data, heh.
That model is over a terabyte, I don’t know why I thought it was lightweight. Not that any reporting on machine learning has been particularly good, but this isn’t what I expected at all.
What can even run it?
A lot, but less than you’d think! Basically a RTX 3090/threadripper system with a lot of RAM (192GB?)
With this framework, specifically: https://github.com/ikawrakow/ik_llama.cpp?tab=readme-ov-file
The “dense” part of the model can stay on the GPU while the experts can be offloaded to the CPU, and the whole thing can be quantized to ~3 bits average, instead of 8 bits like the full model.
That’s just a hack for personal use, though. The intended way to run it is on a couple of H100 boxes, and to serve it to many, many, many users at once. LLMs run more efficiently when they serve in parallel. Eg generating tokens for 4 users isn’t much slower than generating them for 2, and Deepseek explicitly architected it to be really fast at scale. It is “lightweight” in a sense.
…But if you have a “sane” system, it’s indeed a bit large. The best I can run on my 24GB vram system are 32B - 49B dense models (like Qwen 3 or nemotron), or 70B mixture of experts (like the new Hunyuan 70B).
Data centers or a dude with a couple gpus and time on his hands?