Dans-DiscountModels/Retro-YahooAnswers
Preview • Updated • 31 • 4
How to use Dans-DiscountModels/Dans-07YahooAnswers-7b with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("question-answering", model="Dans-DiscountModels/Dans-07YahooAnswers-7b") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Dans-DiscountModels/Dans-07YahooAnswers-7b")
model = AutoModelForCausalLM.from_pretrained("Dans-DiscountModels/Dans-07YahooAnswers-7b")Do you miss the vibes of the early 2000s? Yearn for the nostalgia of internet religious arguments? Then this model is for you!
This was trained on a scrape of Yahoo! Answers from 2007 and received no filtering save for basic sanity checks.
This is not intended for serious use but I think it's charming in a way.
Pygmalion / Metharme
The prompt should start with the cursor on the same line directly after "<|model|>" with no space. The following are all valid formats and can be extended to as many rounds as desired.
<|system|>system message here<|user|>user message here<|model|>
<|system|>system message here<|user|>user message here<|model|>model message<|user|>user message here<|model|>
<|system|>system message here<|model|>
<|system|>system message here<|model|>model message<|user|>user message here<|model|>
Base model
mistralai/Mistral-7B-v0.1