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 Int8 by Tele-AI

 »  All LLMs  »  Tele-AI  »  Telechat 7B Int8   URL Share it on

  11   
  Arxiv:1910.07467   Arxiv:2002.05202   Arxiv:2104.09864   Arxiv:2401.03804   8bit   Autotrain compatible   Custom code   Gptq   Quantized   Region:us   Telechat
Model Card on HF 🤗: https://huggingface.co/Tele-AI/telechat-7B-int8 

Telechat 7B Int8 Benchmarks

LLME Score: 0.13695
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Telechat 7B Int8 (Tele-AI/telechat-7B-int8)
🌟 Advertise your project 🚀

Telechat 7B Int8 Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Long document generation, Work summaries, PPT outlines, Reports, Emails
Limitations:
Possible unseen ethical issues, Need for compliance in use cases
Supported Languages 
Chinese (High), English (High)
Training Details 
Data Sources:
Web pages, Books, Official Media
Data Volume:
1.5 trillion tokens
Model Architecture:
Decoder-only architecture with improvements like Rotary Embedding for position encoding, use of SwiGLU activation function, and RMSNorm based Pre-Normalization.
Input Output 
Input Format:
Tokenized text input expected.
Accepted Modalities:
Text
Output Format:
Generated Text
Performance Tips:
Utilize quantized models for memory efficiency.
Release Notes 
Version:
7B
Date:
2024.01.10
Notes:
Released 7B chat model and quantized versions.
Version:
12B
Date:
2024.01.29
Notes:
To be released
LLM NameTelechat 7B Int8
Repository 🤗https://huggingface.co/Tele-AI/telechat-7B-int8 
Model Size7b
Required VRAM8 GB
Updated2025-09-26
MaintainerTele-AI
Model Typetelechat
Model Files  8.0 GB
GPTQ QuantizationYes
Quantization Typegptq|8bit
Model ArchitectureTelechatForCausalLM
Licenseapache-2.0
Transformers Version4.30.0
Tokenizer ClassBloomTokenizerFast
Padding Token<pad>
Vocabulary Size160256
Torch Data Typefloat16

Best Alternatives to Telechat 7B Int8

Best Alternatives
Context / RAM
Downloads
Likes
Telechat 7B Int40K / 4.7 GB2376
Telechat 7B0K / 0.4 GB149108
Note: green Score (e.g. "73.2") means that the model is better than Tele-AI/telechat-7B-int8.

Rank the Telechat 7B Int8 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