⚠️ ARCHIVED / LEGACY MODEL NOTICE
This repository is part of a legacy collection quantized around 2023. To manage storage quotas and maintain active community projects, some rarely used quantization formats (e.g., Q2_K, Q3_K, Q4_1, Q5_1) have been permanently removed.
Only the most popular and stable formats (Q4_0, Q4_K_M, Q5_K_M, Q6_K, and Q8_0) remain available.
💡 Looking for something modern?
If you are starting a new project, we highly recommend using newer architectures (like Llama 3, Mistral, or Qwen) provided by official maintainers or active community members (e.g., Bartowski, TheBloke legacy files, or official organization handles).
⚠️ This repository is no longer actively maintained. Existing files are provided "as is" for archival and legacy hardware purposes.
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
japanese-stablelm-3b-4e1t-instruct - GGUF
StableLM
This is a Model based on StableLM.
Stablelm is a familiy of Language Models by Stability AI.
Note:
Current (as of 2023-11-15) implementations of Llama.cpp only support GPU offloading up to 34 Layers with these StableLM Models.
The model will crash immediately if -ngl is larger than 34.
The model works fine however without any gpu acceleration.
About GGUF format
gguf is the current file format used by the
ggml library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the
llama.cpp project by Georgi Gerganov
Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are legacy quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not real K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
Original Model Card:
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
1import torch
2from transformers import AutoTokenizer, AutoModelForCausalLM
3
4tokenizer = AutoTokenizer.from_pretrained("stabilityai/japanese-stablelm-3b-4e1t-instruct")
5model = AutoModelForCausalLM.from_pretrained(
6 "stabilityai/japanese-stablelm-3b-4e1t-instruct",
7 trust_remote_code=True,
8 torch_dtype="auto",
9)
10model.eval()
11
12if torch.cuda.is_available():
13 model = model.to("cuda")
14
15def build_prompt(user_query, inputs="", sep="\n\n### "):
16 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。"
17 p = sys_msg
18 roles = ["指示", "応答"]
19 msgs = [": \n" + user_query, ": \n"]
20 if inputs:
21 roles.insert(1, "入力")
22 msgs.insert(1, ": \n" + inputs)
23 for role, msg in zip(roles, msgs):
24 p += sep + role + msg
25 return p
26
27# Infer with prompt without any additional input
28user_inputs = {
29 "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。",
30 "inputs": "情けは人のためならず"
31}
32prompt = build_prompt(**user_inputs)
33
34input_ids = tokenizer.encode(
35 prompt,
36 add_special_tokens=False,
37 return_tensors="pt"
38)
39
40tokens = model.generate(
41 input_ids.to(device=model.device),
42 max_new_tokens=256,
43 temperature=1,
44 top_p=0.95,
45 do_sample=True,
46)
47
48out = tokenizer.decode(tokens[0][input_ids.shape[1]:], skip_special_tokens=True).strip()
49print(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.
End of original Model File
Please consider to support my work
Coming Soon: I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
