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

TeleChat 12B Int4 by Tele-AI

 ยป  All LLMs  ยป  Tele-AI  ยป  TeleChat 12B Int4   URL Share it on

  21   
  Arxiv:1910.07467   Arxiv:2002.05202   Arxiv:2104.09864   Arxiv:2401.03804   4bit   Autotrain compatible   Custom code   Gptq   Quantized   Region:us   Telechat
Model Card on HF ๐Ÿค—: https://huggingface.co/Tele-AI/TeleChat-12B-int4 

TeleChat 12B Int4 Benchmarks

LLME Score: 0.14378
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TeleChat 12B Int4 (Tele-AI/TeleChat-12B-int4)
๐ŸŒŸ Advertise your project ๐Ÿš€

TeleChat 12B Int4 Parameters and Internals

Model Type 
text generation, multilingual
Use Cases 
Areas:
Research, Commercial
Applications:
Natural Language Processing, Human-Computer Interaction
Primary Use Cases:
Q&A, Knowledge Discussion, Code Generation, Mathematical Problem Solving
Considerations:
Requires adherence to usage policy for security and compliance
Supported Languages 
Chinese (high), English (high)
Training Details 
Data Sources:
็ฝ‘้กต, ไนฆ็ฑ, ๅฎ˜ๆ–นๅช’ไฝ“
Data Volume:
3 trillion tokens for 12B model
Methodology:
Scientific data ratio and curriculum learning techniques with automated performance evaluations
Model Architecture:
Decoder-only with enhancements like Rotary Embedding, SwiGLU activation, RMSNorm, and decoupled word embeddings and output layers
Safety Evaluation 
Ethical Considerations:
Model training data compliance was ensured to the best ability
Input Output 
Input Format:
Text prompts
Accepted Modalities:
text
Output Format:
Generated text
Release Notes 
Version:
7B-Release
Date:
2024-01-10
Notes:
Released 7B chat model and quantized version
Version:
12B-Release
Date:
2024-03-20
Notes:
Released 12B chat model and quantized version
LLM NameTeleChat 12B Int4
Repository ๐Ÿค—https://huggingface.co/Tele-AI/TeleChat-12B-int4 
Model Size12b
Required VRAM8.3 GB
Updated2025-09-23
MaintainerTele-AI
Model Typetelechat
Model Files  8.3 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureTelechatForCausalLM
Licenseapache-2.0
Model Max Length100000000
Transformers Version4.24.0
Tokenizer ClassTelechatTokenizer
End of Sentence Token<_end>
Unk Token<_end>
Vocabulary Size120000

Best Alternatives to TeleChat 12B Int4

Best Alternatives
Context / RAM
Downloads
Likes
TeleChat 12B Int80K / 13.9 GB232
TeleChat 12B V20K / 5.9 GB241
TeleChat 12B0K / 5.9 GB2811
Note: green Score (e.g. "73.2") means that the model is better than Tele-AI/TeleChat-12B-int4.

Rank the TeleChat 12B Int4 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? 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