GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing huggingface.co โ PygmalionAI/metharme-7b ยท Hugging Face Metharme 7BAn instruction-tuned LLaMA biased towards fiction writing and conversation.Model DetailsMetharme 7B is an instruct model based on Meta's LLaMA-7B. This is an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, but which can be guided using natural language like other instruct models. See the prompting section below for examples. It was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically generated instructions attached. Applying the XORsThe model weights in this repository cannot be used as-is. The files here are XORs due to licensing concerns. To obtain proper, usable model weights you need to:
Note for Windows users: If you're on Windows, you might run into issues where following the steps above will result in corrupted files. This seems to be because
PromptingThe current model version has been trained on prompts using three different roles, which are denoted by the following tokens: The Prompting exampleHere's a concrete example. Let's say you have the following system prompt:
And the user has typed in the following message:
To perform inference against the model, the prompt should be formatted like this:
The model might generate something like:
It will automatically emit an end-of-text token ( Pretend then that the user has replied with
Which might generate something like:
Same process applies. Usually, it is best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window. Limitations and biasesThe intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope. As such, it was not fine-tuned to be safe and harmless: the base model and this fine-tune have been trained on data known to contain profanity and texts that are lewd or otherwise offensive. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading. Inference Providers NEW This model isn't deployed by any Inference Provider. ๐ Ask for provider support |
| You are visitor 01402605 โ GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800ร600. No cookies required. |