LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

SpeechGPT 7B Cm by fnlp

 »  All LLMs  »  fnlp  »  SpeechGPT 7B Cm   URL Share it on

  109   

SpeechGPT 7B Cm is an open-source language model by fnlp. Features: 7b LLM, VRAM: 27GB, Context: 2K, LLM Explorer Score: 0.1.

  Arxiv:2305.11000   Arxiv:2308.16692   Autotrain compatible   Endpoints compatible   Llama   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/fnlp/SpeechGPT-7B-cm 

SpeechGPT 7B Cm Benchmarks

LLME Score: 0.09605
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SpeechGPT 7B Cm (fnlp/SpeechGPT-7B-cm)
🌟 Advertise your project 🚀

SpeechGPT 7B Cm Parameters and Internals

Model Type 
multi-modal, conversational, instruction-following
Use Cases 
Areas:
Research, Personal Assistance, Education
Applications:
Personal assistant, Chat partner, Poet, Psychologist, Educational assistant
Primary Use Cases:
Talking encyclopedia
Considerations:
Model performance currently not optimal due to limited training resources
Additional Notes 
Foundational model for speech language model research exploration
Supported Languages 
English (High)
Training Details 
Data Sources:
LibriLight
Data Volume:
9 million unit-text data pairs
Methodology:
Three-stage training with modality-adaptation pre-training, cross-modal instruction fine-tuning, and chain-of-modality instruction fine-tuning.
Model Architecture:
Based on LLaMA-7B architecture
Responsible Ai Considerations 
Transparency:
Limited due to early-stage research exploration
Accountability:
Fudan University
Input Output 
Input Format:
Text and Speech inputs using <mHubert format>
Accepted Modalities:
Text, Speech
Output Format:
Textual and audio (.wav) outputs
Performance Tips:
Download required checkpoints and datasets for optimal performance.
Release Notes 
Version:
2023/9/15
Date:
2023-09-15
Notes:
Released SpeechGPT code and checkpoints
Version:
2023/9/1
Date:
2023-09-01
Notes:
Proposed SpeechTokenizer and released associated assets
Version:
2023/5/18
Date:
2023-05-18
Notes:
Introduced SpeechGPT, capable of following multi-modal human instructions
LLM NameSpeechGPT 7B Cm
Repository 🤗https://huggingface.co/fnlp/SpeechGPT-7B-cm 
Model Size7b
Required VRAM27 GB
Updated2025-09-23
Maintainerfnlp
Model Typellama
Model Files  27.0 GB
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.29.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size33006
Torch Data Typefloat16

Best Alternatives to SpeechGPT 7B Cm

Best Alternatives
Context / RAM
Downloads
Likes
1241024K / 16.1 GB930
1621024K / 16.1 GB600
1571024K / 16.1 GB1010
1181024K / 16.1 GB150
A5.41024K / 16.1 GB120
A6 L1024K / 16.1 GB2010
A3.41024K / 16.1 GB130
A2.41024K / 16.1 GB120
M1024K / 16.1 GB1270
2 Very Sci Fi1024K / 16.1 GB3170
Note: green Score (e.g. "73.2") means that the model is better than fnlp/SpeechGPT-7B-cm.

Rank the SpeechGPT 7B Cm 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? 52509 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer