AnyGPT Chat by fnlp

 ยป  All LLMs  ยป  fnlp  ยป  AnyGPT Chat   URL Share it on

  Arxiv:2402.12226   Autotrain compatible   Dataset:fnlp/anyinstruct   En   Endpoints compatible   Llama   Pytorch   Region:us
Model Card on HF ๐Ÿค—: https://huggingface.co/fnlp/AnyGPT-chat 

AnyGPT Chat Benchmarks

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

AnyGPT Chat Parameters and Internals

Model Type 
multimodal
Use Cases 
Areas:
research, commercial applications
Applications:
image captioning, speech recognition, text-to-speech, text-to-music, music captioning
Primary Use Cases:
text-to-image, speech synthesis, automatic speech recognition
Additional Notes 
The model's generation may still be unstable due to limitations in data and training resources. It is suggested to try different decoding strategies or multiple generations for optimal results.
Supported Languages 
English (proficient)
Training Details 
Data Sources:
fnlp/AnyInstruct
Methodology:
Generative training scheme that converts all modal data into a unified discrete representation using the Next Token Prediction task.
Model Architecture:
Discrete Sequence Modeling
Input Output 
Input Format:
Discrete representations for text, image, speech, and music
Accepted Modalities:
text, image, speech, music
Output Format:
Various modalities including text, speech (wav), image (jpg), and music (wav)
Performance Tips:
Refer to decoding configuration files for optimizing model performance.
LLM NameAnyGPT Chat
Repository ๐Ÿค—https://huggingface.co/fnlp/AnyGPT-chat 
Required VRAM27.7 GB
Updated2025-02-22
Maintainerfnlp
Model Typellama
Model Files  27.7 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size53520
Torch Data Typefloat32

Best Alternatives to AnyGPT Chat

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text 512K512K / 13.5 GB102
LWM Text Chat 512K512K / 13.5 GB62
LWM Text 256K256K / 13.5 GB263
LWM Text Chat 256K256K / 13.5 GB213
Pallas 0.5 LASER 0.1195K / 68.9 GB19912
Ashley3b X 1.2128K / 6.5 GB250
Ashley3b X 1.3128K / 6.5 GB140
Cyber13128K / 16.1 GB50
Cyber8128K / 16.1 GB50
LWM Text Chat 128K128K / 13.5 GB4120
Note: green Score (e.g. "73.2") means that the model is better than fnlp/AnyGPT-chat.

Rank the AnyGPT Chat Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227