Name	Quant method	Size
japanese-stablelm-3b-4e1t-instruct.Q2_K.gguf	Q2_K	1.01GB
japanese-stablelm-3b-4e1t-instruct.IQ3_XS.gguf	IQ3_XS	1.11GB
japanese-stablelm-3b-4e1t-instruct.IQ3_S.gguf	IQ3_S	1.17GB
japanese-stablelm-3b-4e1t-instruct.Q3_K_S.gguf	Q3_K_S	1.17GB
japanese-stablelm-3b-4e1t-instruct.IQ3_M.gguf	IQ3_M	1.23GB
japanese-stablelm-3b-4e1t-instruct.Q3_K.gguf	Q3_K	1.3GB
japanese-stablelm-3b-4e1t-instruct.Q3_K_M.gguf	Q3_K_M	1.3GB
japanese-stablelm-3b-4e1t-instruct.Q3_K_L.gguf	Q3_K_L	1.4GB
japanese-stablelm-3b-4e1t-instruct.IQ4_XS.gguf	IQ4_XS	1.43GB
japanese-stablelm-3b-4e1t-instruct.Q4_0.gguf	Q4_0	1.5GB
japanese-stablelm-3b-4e1t-instruct.IQ4_NL.gguf	IQ4_NL	1.51GB
japanese-stablelm-3b-4e1t-instruct.Q4_K_S.gguf	Q4_K_S	1.51GB
japanese-stablelm-3b-4e1t-instruct.Q4_K.gguf	Q4_K	1.59GB
japanese-stablelm-3b-4e1t-instruct.Q4_K_M.gguf	Q4_K_M	1.59GB
japanese-stablelm-3b-4e1t-instruct.Q4_1.gguf	Q4_1	1.65GB
japanese-stablelm-3b-4e1t-instruct.Q5_0.gguf	Q5_0	1.81GB
japanese-stablelm-3b-4e1t-instruct.Q5_K_S.gguf	Q5_K_S	1.81GB
japanese-stablelm-3b-4e1t-instruct.Q5_K.gguf	Q5_K	1.86GB
japanese-stablelm-3b-4e1t-instruct.Q5_K_M.gguf	Q5_K_M	1.86GB
japanese-stablelm-3b-4e1t-instruct.Q5_1.gguf	Q5_1	1.96GB
japanese-stablelm-3b-4e1t-instruct.Q6_K.gguf	Q6_K	2.14GB
japanese-stablelm-3b-4e1t-instruct.Q8_0.gguf	Q8_0	2.77GB

Original model description:

language:

ja tags:
japanese-stablelm
causal-lm pipeline_tag: text-generation license: apache-2.0 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-3B-4E1T Instruct

Model Description

This is a 3B-parameter decoder-only Japanese language model fine-tuned on instruction-following datasets, built on top of the base model Japanese StableLM-3B-4E1T Base.

If you are in search of a larger model, please check Japanese Stable LM Instruct Gamma 7B.

Usage

python

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/japanese-stablelm-3b-4e1t-instruct")
model = AutoModelForCausalLM.from_pretrained(
  "stabilityai/japanese-stablelm-3b-4e1t-instruct",
  trust_remote_code=True,
  torch_dtype="auto",
)
model.eval()

if torch.cuda.is_available():
    model = model.to("cuda")

def build_prompt(user_query, inputs="", sep="\n\n### "):
    sys_msg = "以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。"
    p = sys_msg
    roles = ["指示", "応答"]
    msgs = [": \n" + user_query, ": \n"]
    if inputs:
        roles.insert(1, "入力")
        msgs.insert(1, ": \n" + inputs)
    for role, msg in zip(roles, msgs):
        p += sep + role + msg
    return p

# Infer with prompt without any additional input
user_inputs = {
    "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。",
    "inputs": "情けは人のためならず"
}
prompt = build_prompt(**user_inputs)

input_ids = tokenizer.encode(
    prompt, 
    add_special_tokens=False, 
    return_tensors="pt"
)

tokens = model.generate(
    input_ids.to(device=model.device),
    max_new_tokens=256,
    temperature=1,
    top_p=0.95,
    do_sample=True,
)

out = tokenizer.decode(tokens[0][input_ids.shape[1]:], skip_special_tokens=True).strip()
print(out)

Model Details

Developed by: Stability AI
Model type: Japanese StableLM-3B-4E1T Instruct model is an auto-regressive language model based on the transformer decoder architecture.
Language(s): Japanese
License: This model is licensed under Apache License, Version 2.0.
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.

Model Architecture

The model is a decoder-only transformer similar to the LLaMA (Touvron et al., 2023) architecture with the following modifications:

Parameters	Hidden Size	Layers	Heads	Sequence Length
2,795,443,200	2560	32	32	4096

Position Embeddings: Rotary Position Embeddings (Su et al., 2021) applied to the first 25% of head embedding dimensions for improved throughput following Black et al. (2022).
Normalization: LayerNorm (Ba et al., 2016) with learned bias terms as opposed to RMSNorm (Zhang & Sennrich, 2019).
Tokenizer: GPT-NeoX (Black et al., 2022).

Training Datasets

Use and Limitations

Intended Use

The model is intended to be used by all individuals as a foundational model 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.

Credits

The fine-tuning was carried out by Fujiki Nakamura. Other aspects, including data preparation and evaluation, were handled by the Language Team of Stability AI Japan, notably Meng Lee, Makoto Shing, Paul McCann, Naoki Orii, and Takuya Akiba.

Acknowledgements

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.

RichardErkhov/stabilityai_-_japanese-stablelm-3b-4e1t-instruct-gguf