metadata

license: apache-2.0
datasets:
  - OpenAssistant/oasst1
  - zetavg/ShareGPT-Processed
  - augmxnt/ultra-orca-boros-en-ja-v1
language:
  - ja
  - en

drawing

How to use

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-7B-chat")
model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-7B-chat", torch_dtype=torch.bfloat16, device_map="auto")

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})

prompt = tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)

pipe(prompt, max_new_tokens=100, do_sample=False, temperature=0.0, return_full_text=False)

Base checkpoint

lightblue/karasu-7B

Training datasets (total ~7B)

Lightblue's suite of Kujira datasets (unreleased)
Lightblue's own question-based datasets (unreleased)
Lightblue's own category-based datasets (unreleased)
OASST (Japanese chats only)
ShareGPT (Japanese chats only)
augmxnt/ultra-orca-boros-en-ja-v1 (['airoboros', 'slimorca', 'ultrafeedback', 'airoboros_ja_new'] only)

Developed by

Engineers

Peter Devine

Sho Higuchi

Advisors

Yuuki Yamanaka

Atom Sonoda

Dataset evaluator

Renju Aoki