VNTL v3.5.1 EXL2 quantization branches

  • main (4.0bpw)
  • 5.6bpw
  • 8.0bpw

original (unquantized): https://huggingface.co/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 (η“œη”Ÿ 新吾) | Gender: Male | Aliases: Onii-chan (γŠε…„γ‘γ‚ƒγ‚“)
Name: Uryuu Sakuno (η“œη”Ÿ ζ‘œδΉƒ) | Gender: Female
<<JAPANESE>>
[ζ‘œδΉƒ]: γ€Žβ€¦β€¦γ”γ‚γ‚“γ€
<<ENGLISH>> (fidelity = absolute)
[Sakuno]: γ€Ž... Sorry.』</s>
<<JAPANESE>>
[新吾]: γ€Œγ†γ†γ‚“γ€γ“γ†θ¨€γ£γ‘γ‚ƒγͺγ‚“γ γ‘γ©γ€θΏ·ε­γ§γ‚ˆγ‹γ£γŸγ‚ˆγ€‚ζ‘œδΉƒγ―ε―ζ„›γ„γ‹γ‚‰γ€γ„γ‚γ„γ‚εΏƒι…γ—γ‘γ‚ƒγ£γ¦γŸγ‚“γ γžδΏΊγ€
<<ENGLISH>> (fidelity = high)

The generated translation for that prompt, with temperature 0, is:

[Shingo]: γ€ŒNo, don't apologize. I'm just glad you're safe. You're so cute, Sakuno, I was worried sick.」
Downloads last month
10
Safetensors
Model size
967M params
Tensor type
I32
Β·
FP16
Β·
I16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Dataset used to train robbie0/vntl-7b-v0.3.1-hf-exl2