Data Efficient Training Of LLMs V1 By ChiyuSONG: Benchmarks, Features and Detailed Analysis. Insights on Data Efficient Training Of LLMs V1.

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 Benchmarks

LLME Score: 0.14908

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Data Efficient Training Of LLMs V1 (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	2024-12-26
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

Best Alternatives to Data Efficient Training Of LLMs V1

Best Alternatives	Context / RAM	Downloads	Likes
Blossom V2 Baichuan 13B	0K / 26.5 GB	13	1
Baichuan 13B Instruction	0K / 26.5 GB	30	6
Baichuan 13B Instruction GPTQ	0K / 7.9 GB	15	4

Rank the Data Efficient Training Of LLMs V1 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 40303 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Release v20241227

Support LLM Explorer

Data Efficient Training Of LLMs V1 by ChiyuSONG

» All LLMs » ChiyuSONG » Data Efficient Training Of LLMs V1 URL Share it on

Data Efficient Training Of LLMs V1 Benchmarks

Data Efficient Training Of LLMs V1 Parameters and Internals

Best Alternatives to Data Efficient Training Of LLMs V1

Rank the Data Efficient Training Of LLMs V1 Capabilities

What open-source LLMs or SLMs are you in search of? 40303 in total.