license: apache-2.0
Model Card for Ostrich
- Trained with some of the Nostr notes
- Likes to disagree more compared to Llama3. It can be used for refutation, counter argument production.
- Aligned a bit in these domains:
- Health
- Permaculture
- Phytochemicals
- Alternative medicine
- Herbs
- Nutrition
Read more about it here: https://habla.news/a/naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xsunjwfkxcunwv3jvtnjyc
Model Details
- Finetuned from model: https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct
The number in the filenames like 4750 means the version. Higher numbers are newer versions.
Uses
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.
Llama3 chat template can be used. <|begin_of_text|><|start_header_id|> ...
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 ~30 hours for a dataset of about 20MB.