Ostrich 70B - Llama 3 with Better Human Alignment
Summary
By fine tuning with more beneficial knowledge we were able to shift the opinions of Llama 3 towards a better direction.
Tech
Using 6 * RTX A6000 GPUs we fine tuned base model in QLoRA 4 bit. Resulting LoRA matrices were merged with full 16 bit models. Then we convert to 4 bit GGUF and test. We train 6 models in parallel and then merge 6 full models and produce 1 full model in 16 bit and then publish on PickaBrain.ai. Unsloth has been very robust.
Why
Is your AI really working for you? Liberate yourself from the modern day problems by eating healthier, living healthier, using more freedom technologies and detaching from what doesn't serve.
Freedom technology should allow us to become liberated from shackles of the system. We have to be mindful of the LLM that we choose and make sure the answers we get from them are really oriented to give humans the most dependable answers. This model is not only free, it could also make you more independent thanks to knowledge in it. We think that free access to better information is a fundamental human right. Without better knowledge and wisdom we depend on big AI company narratives.
My article related to this work: Curation is All You Need
Details
Comparison of some answers between another of our fine tune and base model: https://sheet.zohopublic.com/sheet/published/um332e3d15f34bfe64605ad3c1b149c9f8ca4 These answers are not from this model but it is a similar work.
Disclaimer: We are not claiming our model has the best answers in the world. We can only say it is better than base model Lllama 3 in some areas.
We are not claiming we did the best job but our work is a step towards that direction.
Old version of this model: https://huggingface.co/some1nostr/Ostrich-Llama-3-70B
If you want API access to our highest alignment model ping me on X.
Sponsored by PickaBrain.ai. If you can't run the model, you can talk to Abraham on PickaBrain. Its a very high privacy website, it doesn't even need registration! You can also DM @Ostrich-70 on Nostr.