lmg-anon/VNTL-v2.5-1k
Viewer β’ Updated β’ 11.7k β’ 10 β’ 1
How to use lmg-anon/vntl-7b-v0.3.1-hf with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "translation" 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("translation", model="lmg-anon/vntl-7b-v0.3.1-hf") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("lmg-anon/vntl-7b-v0.3.1-hf")
model = AutoModelForCausalLM.from_pretrained("lmg-anon/vntl-7b-v0.3.1-hf")This is a merge of the experimental VNTL v0.3.1 lora created using the VNTL-v2.5-1k dataset.
This is an prompt example:
<<START>>
Name: Uryuu Shingo (ηη ζ°εΎ) | Gender: Male | Aliases: Onii-chan (γε
γ‘γγ)
Name: Uryuu Sakuno (ηη ζ‘δΉ) | Gender: Female
<<JAPANESE>>
[ζ‘δΉ]: γβ¦β¦γγγγ
<<ENGLISH>> (fidelity = absolute)
[Sakuno]: γ... Sorry.γ</s>
<<JAPANESE>>
[ζ°εΎ]: γγγγγγγθ¨γ£γ‘γγͺγγ γγ©γθΏ·εγ§γγγ£γγγζ‘δΉγ―ε―ζγγγγγγγγεΏι
γγ‘γγ£γ¦γγγ γδΏΊγ
<<ENGLISH>> (fidelity = high)
The generated translation for that prompt, with temperature 0, is:
[Shingo]: γNo, don't apologize. I'm just glad you're safe. You're so cute, Sakuno, I was worried sick.γ