llama2
extra_gated_fields:
Name: text
Email: text
Country: text
Organization or Affiliation: text
I allow Stability AI to contact me about information related to its models and research: checkbox
Japanese-StableLM-Instruct-Beta-70B
A cute robot wearing a kimono writes calligraphy with one single brush
A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL
Model Description
japanese-stablelm-instruct-beta-70b is a 70B-parameter decoder-only language model based on japanese-stablelm-base-beta-70b and further fine tuned on Databricks Dolly-15k, Anthropic HH, and other public data.
Then start generating text with japanese-stablelm-instruct-beta-70b by using the following code snippet:
python
1import torch
2from transformers import AutoTokenizer, AutoModelForCausalLM
34model_name ="stabilityai/japanese-stablelm-instruct-beta-70b"5tokenizer = AutoTokenizer.from_pretrained(model_name)67# The next line may need to be modified depending on the environment8model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")910defbuild_prompt(user_query, inputs):11 sys_msg ="<s>[INST] <<SYS>>\nあなたは役立つアシスタントです。\n<<SYS>>\n\n"12 p = sys_msg + user_query +"\n\n"+ inputs +" [/INST] "13return p
1415# Infer with prompt without any additional input16user_inputs ={17"user_query":"与えられたことわざの意味を小学生でも分かるように教えてください。",18"inputs":"情けは人のためならず"19}20prompt = build_prompt(**user_inputs)2122input_ids = tokenizer.encode(23 prompt,24 add_special_tokens=True,25 return_tensors="pt"26)2728# this is for reproducibility.29# feel free to change to get different result30seed =2331torch.manual_seed(seed)3233tokens = model.generate(34 input_ids.to(device=model.device),35 max_new_tokens=128,36 temperature=0.99,37 top_p=0.95,38 do_sample=True,39)4041out = tokenizer.decode(tokens[0], skip_special_tokens=True)42print(out)
We suggest playing with different generation config (top_p, repetition_penalty etc) to find the best setup for your tasks. For example, use higher temperature for roleplay task, lower temperature for reasoning.
Model Details
Model type: japanese-stablelm-instruct-beta-70b model is an auto-regressive language model based on the Llama2 transformer architecture.
Contact: For questions and comments about the model, please join Stable Community Japan. For future announcements / information about Stability AI models, research, and events, please follow https://twitter.com/StabilityAI_JP.
Training Dataset
The following datasets were used for the instruction training. Note these are Japanese translated versions of the original datasets, shared by kunishou.
The model is intended to be used by all individuals as a foundation for application-specific fine-tuning without strict limitations on commercial use.
Limitations and bias
The pre-training dataset may have contained offensive or inappropriate content even after applying data cleansing filters which can be reflected in the model generated text. We recommend users exercise reasonable caution when using these models in production systems. Do not use the model for any applications that may cause harm or distress to individuals or groups.
Authors
This model was developed by the Research & Development team at Stability AI Japan, and the development was co-led by Takuya Akiba and Meng Lee. The members of the team are as follows:
We thank Meta Research for releasing Llama 2 under an open license for others to build on.
We are grateful for the contributions of the EleutherAI Polyglot-JA team in helping us to collect a large amount of pre-training data in Japanese. Polyglot-JA members includes Hyunwoong Ko (Project Lead), Fujiki Nakamura (originally started this project when he commited to the Polyglot team), Yunho Mo, Minji Jung, KeunSeok Im, and Su-Kyeong Jang.
We are also appreciative of AI Novelist/Sta (Bit192, Inc.) and the numerous contributors from Stable Community Japan for assisting us in gathering a large amount of high-quality Japanese textual data for model training.
