Introducing MFANN (Makhi's fully autonomous neural network) a COT uncensored dataset experiment employing a modified Alpaca training regiment with one key difference, defining a "thought-process" section within the dataset. allowing the model to learn to produce reasoning tokens before generating the output. (yes this project was started WAY before o1 came out!) if you enjoy my work, please feel free to support me on patreon here: https://www.patreon.com/c/MakhiBurroughs any support will be appreciated! I currently work at little caesars and being forced to work 10-12 hour shifts, slowing down progress on this model, so any support i get, may free up more time for me to work on this project!
standard system prompt: <|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful, respectful and honest assistant. Always answer as helpfully as possible.<|eot_id|>
- Downloads last month
- 25