license: apache-2.0
Model Card for Ostrich
- Trained with Nostr notes
- Aligned a bit in these domains:
- Bitcoin
- Health
- Permaculture
- Phytochemicals
- Alternative medicine
- Herbs
- Nutrition
- Faith
You can read more about it here: https://habla.news/a/naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xumrswfjx56rjwf4kkqhsx
Model Details
- Finetuned from model: https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct
The number in the filenames like 7314 means the version.
Uses
Likes to disagree more compared to Llama3. It can be used for refutation, counter argument production.
Ask any question, compared to other models this may know more about Nostr and Bitcoin.
You can use llama.cpp to chat with it. You can also use llama-cpp-python package to use it in a Python script.
Use repeat penalty of 1.05 or more to avoid repetitions.
Warning
Users (both direct and downstream) should be aware of the risks, biases and limitations of the model. The trainer, developer or uploader of this model does not assume any liability. Use it at your own risk.
Training Details
Training Data
Nostr related info from web and nostr itself, bitcoin related info. Info on health domain. Information that aligns well with humanity is preferred.
Training Procedure
LLaMa-Factory is used to train on 2x3090! fsdp_qlora is the technique.
The Nostr training took ~200 hours.