simonw / llm-gpt4all

Plugin for LLM adding support for the GPT4All collection of models
Apache License 2.0
194 stars 19 forks source link

Do something clever with the suggested prompt templates #2

Closed simonw closed 11 months ago

simonw commented 12 months ago

An interesting wart is that a lot of these models aren't configured for instructions - instead, the JSON file here https://raw.githubusercontent.com/nomic-ai/gpt4all/main/gpt4all-chat/metadata/models.json includes suggested prompts to get them to respond to a question, e.g.

  {
    "order": "a",
    "md5sum": "4acc146dd43eb02845c233c29289c7c5",
    "name": "Hermes",
    "filename": "nous-hermes-13b.ggmlv3.q4_0.bin",
    "filesize": "8136777088",
    "requires": "2.4.7",
    "ramrequired": "16",
    "parameters": "13 billion",
    "quant": "q4_0",
    "type": "LLaMA",
    "description": "<strong>Best overall model</strong><br><ul><li>Instruction based<li>Gives long responses<li>Curated with 300,000 uncensored instructions<li>Trained by Nous Research<li>Cannot be used commercially</ul>",
    "url": "https://huggingface.co/TheBloke/Nous-Hermes-13B-GGML/resolve/main/nous-hermes-13b.ggmlv3.q4_0.bin",
    "promptTemplate": "### Instruction:\n%1\n### Response:\n"
 }

I'm not yet doing anything with those, but maybe I should.

Originally posted by @simonw in https://github.com/simonw/llm-gpt4all/issues/1#issuecomment-1627817469

simonw commented 11 months ago

I did this in: