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

Telechat 7B by Tele-AI

 »  All LLMs  »  Tele-AI  »  Telechat 7B   URL Share it on

  149   
  Arxiv:1910.07467   Arxiv:2002.05202   Arxiv:2104.09864   Arxiv:2401.03804   Autotrain compatible   Custom code   Pytorch   Region:us   Telechat
Model Card on HF 🤗: https://huggingface.co/Tele-AI/telechat-7B 

Telechat 7B Benchmarks

LLME Score: 0.14181
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Telechat 7B (Tele-AI/telechat-7B)
🌟 Advertise your project 🚀

Telechat 7B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
text generation tasks, conversational interfaces
Limitations:
potential bias, inaccurate or harmful generation
Considerations:
Ensure legality and security when deploying.
Additional Notes 
TeleChat supports deepspeed fine-tuning with Zero parallel memory optimization and has been enhanced for multi-round capabilities and long-text generation.
Training Details 
Data Sources:
网页, 书籍, 官方媒体
Data Volume:
1TB
Methodology:
标准的 Decoder-only 结构，使用 Rotary Embedding 和 SwiGLU 激活函数
Hardware Used:
deepspeed
Model Architecture:
标准的 Decoder-only 结构，使用 Rotary Embedding 和 SwiGLU 激活函数，词嵌入层与输出层解耦
Release Notes 
Version:
7B
Date:
2024.1.10
Notes:
Released 7B version chat model and quantized versions.
Version:
12B
Date:
2024.3.20
Notes:
Released 12B version chat model and quantized versions.
Date:
2024.1.11
Notes:
Released 1TB Chinese dataset.
LLM NameTelechat 7B
Repository 🤗https://huggingface.co/Tele-AI/telechat-7B 
Model Size7b
Required VRAM0.4 GB
Updated2025-09-23
MaintainerTele-AI
Model Typetelechat
Model Files  1.3 GB: 1-of-32   0.4 GB: 2-of-32   0.4 GB: 3-of-32   0.4 GB: 4-of-32   0.4 GB: 5-of-32   0.4 GB: 6-of-32   0.4 GB: 7-of-32   0.4 GB: 8-of-32   0.4 GB: 9-of-32   0.4 GB: 10-of-32   0.4 GB: 11-of-32   0.4 GB: 12-of-32   0.4 GB: 13-of-32   0.4 GB: 14-of-32   0.4 GB: 15-of-32   0.4 GB: 16-of-32   0.4 GB: 17-of-32   0.4 GB: 18-of-32   0.4 GB: 19-of-32   0.4 GB: 20-of-32   0.4 GB: 21-of-32   0.4 GB: 22-of-32   0.4 GB: 23-of-32   0.4 GB: 24-of-32   0.4 GB: 25-of-32   0.4 GB: 26-of-32   0.4 GB: 27-of-32   0.4 GB: 28-of-32   0.4 GB: 29-of-32   0.4 GB: 30-of-32   0.4 GB: 31-of-32   0.0 GB: 32-of-32
Model ArchitectureTelechatForCausalLM
Licenseapache-2.0
Transformers Version4.30.0
Tokenizer ClassBloomTokenizerFast
Padding Token<pad>
Vocabulary Size160256

Best Alternatives to Telechat 7B

Best Alternatives
Context / RAM
Downloads
Likes
Telechat 7B Int80K / 8 GB1181
Telechat 7B Int40K / 4.7 GB2376

Rank the Telechat 7B 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? 51544 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 v20241124
  Support LLM Explorer