What are the hardware requirements for Data Efficient Training Of LLMs V1?

Data Efficient Training Of LLMs V1 requires approximately 29.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Data Efficient Training Of LLMs V1 and how large is it?

Data Efficient Training Of LLMs V1 is developed by ChiyuSONG, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Data Efficient Training Of LLMs V1?

Data Efficient Training Of LLMs V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Data Efficient Training Of LLMs V1 by ChiyuSONG — VRAM 29.1GB

Name: Data Efficient Training Of LLMs V1
Author: ChiyuSONG

Data Efficient Training Of LLMs V1 is an open-source language model by ChiyuSONG. Features: 13b LLM, VRAM: 29.1GB, License: mit, Instruction-Based, LLM Explorer Score: 0.09.

Arxiv:2310.19651 Autotrain compatible Baichuan Custom code Dataset:chiyusong/dynamics-of-... Endpoints compatible Instruct Pytorch Region:us Zh

Model Card on HF 🤗: https://huggingface.co/ChiyuSONG/data-efficient-training-of-LLMs-v1

Data Efficient Training Of LLMs V1 Parameters and Internals

Model Type

instruction tuning, large language model

Additional Notes

The project explores efficient data usage for training large language models, focusing on the dynamics of instruction tuning to improve diverse capabilities.

Supported Languages

zh (Proficient)

Training Details

Data Sources:

ChiyuSONG/dynamics-of-instruction-tuning

Methodology:

Utilizes a progressive instruction tuning approach to enhance model abilities based on different factor influences.

Release Notes

Version:

Notes:

Focus on instruction fine-tuning process, utilizing multiple capabilities categories such as creative writing, code generation, logical reasoning.

LLM Name	Data Efficient Training Of LLMs V1
Repository 🤗	https://huggingface.co/ChiyuSONG/data-efficient-training-of-LLMs-v1
Model Size	13b
Required VRAM	29.1 GB
Updated	2025-03-03
Maintainer	ChiyuSONG
Model Type	baichuan
Instruction-Based	Yes
Model Files	29.1 GB
Supported Languages	zh
Model Architecture	BaichuanForCausalLM
License	mit
Model Max Length	4096
Transformers Version	4.30.2
Tokenizer Class	BaichuanTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	125696
Torch Data Type	bfloat16

Rank the Data Efficient Training Of LLMs V1 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Data Efficient Training Of LLMs V1

Best Alternatives	Context / RAM	Downloads	Likes
Blossom V2 Baichuan 13B	0K / 26.5 GB	14	1
NSFW 13B Sft	0K / 26.5 GB	29	106
Baichuan 13B Instruction	0K / 26.5 GB	11	6
Baichuan 13B Instruction GPTQ	0K / 7.9 GB	8	4