Quantization made by Richard Erkhov.
japanese-stablelm-instruct-ja_vocab-beta-7b - GGUF
- Model creator: https://huggingface.co/stabilityai/
- Original model: https://huggingface.co/stabilityai/japanese-stablelm-instruct-ja_vocab-beta-7b/
Original model description:
language: - ja tags: - japanese-stablelm - causal-lm pipeline_tag: text-generation datasets: - kunishou/hh-rlhf-49k-ja - kunishou/databricks-dolly-15k-ja - kunishou/oasst1-89k-ja license: - 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-JAVocab-Beta-7B
A cute robot wearing a kimono writes calligraphy with one single brush โ Stable Diffusion XL
Model Description
japanese-stablelm-instruct-ja_vocab-beta-7b is a 7B-parameter decoder-only language model based on japanese-stablelm-ja_vocab-beta-7b and further fine tuned on Databricks Dolly-15k, Anthropic HH, and other public data.
Compared to the standard base model, this model uses a tokenizer with an expanded vocabulary derived from Japanese data. This allows it to represent the same amount of text with fewer tokens, which speeds up inference significantly.
Usage
First install additional dependencies in requirements.txt:
pip install -r requirements.txt
Then start generating text with japanese-stablelm-instruct-ja_vocab-beta-7b by using the following code snippet:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "stabilityai/japanese-stablelm-instruct-ja_vocab-beta-7b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
# The next line may need to be modified depending on the environment
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
def build_prompt(user_query, inputs):
sys_msg = "<s>[INST] <<SYS>>\nใใชใใฏๅฝน็ซใคใขใทในใฟใณใใงใใ\n<<SYS>>\n\n"
p = sys_msg + user_query + "\n\n" + inputs + " [/INST] "
return p
user_inputs = {
"user_query": "ไธใใใใใใจใใใฎๆๅณใๅฐๅญฆ็ใงใๅใใใใใซๆใใฆใใ ใใใ",
"inputs": "ๆ
ใใฏไบบใฎใใใชใใ"
}
prompt = build_prompt(**user_inputs)
input_ids = tokenizer.encode(
prompt,
add_special_tokens=True,
return_tensors="pt"
)
# this is for reproducibility.
# feel free to change to get different result
seed = 23
torch.manual_seed(seed)
tokens = model.generate(
input_ids.to(device=model.device),
max_new_tokens=128,
temperature=0.99,
top_p=0.95,
do_sample=True,
)
out = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(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-ja_vocab-beta-7bmodel is an auto-regressive language model based on the Llama2 transformer architecture. - Language(s): Japanese
- License: Llama2 Community License.
- 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.
Use and Limitations
Intended Use
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:
Acknowledgements
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.
- Downloads last month
- 587