# pip install -U transformers accelerate
# 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", device_map="auto")Quick Links
Description
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.
Prompt format:
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|>
Some quick and dirty training details:
- Sequence length: 2048
- Training time: 32 hours
- Hardware: 1x RTX 4080
- Training type: QLoRA
- PEFT R/A: 32/32
- Downloads last month
- 27
Model tree for Dans-DiscountModels/Dans-07YahooAnswers-7b
Base model
mistralai/Mistral-7B-v0.1
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="Dans-DiscountModels/Dans-07YahooAnswers-7b")