lightblue/karasu-7B-chat-plus-unleashed

Evaluation

How to use

Hugggingface

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-7B-chat-plus-unleashed")
model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-7B-chat-plus-unleashed", 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)

VLLM

from vllm import LLM, SamplingParams

sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
llm = LLM(model="lightblue/karasu-7B-chat-plus-unleashed")

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 = llm.llm_engine.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
prompts = [prompt]

outputs = llm.generate(prompts, sampling_params)
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

Base checkpoint

lightblue/karasu-7B

Training datasets (total ~7B)

The same as the 'plus' checkpoint, but with about 6K refusals ("申し訳ありませんが、。。。") filtered out from the category dataset

• 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

Project manager

Shunichi Taniguchi

Dataset evaluator

Renju Aoki