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

LongAlign 6B 64K by THUDM

 »  All LLMs  »  THUDM  »  LongAlign 6B 64K   URL Share it on

  42   
  Arxiv:2401.18058   Chatglm   Custom code   Dataset:thudm/longalign-10k   En   Feature-extraction   Long context   Pytorch   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/THUDM/LongAlign-6B-64k 

LongAlign 6B 64K Benchmarks

LLME Score: 0.16214
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LongAlign 6B 64K (THUDM/LongAlign-6B-64k)

LongAlign 6B 64K Parameters and Internals

Model Type 
text generation, chat
Use Cases 
Areas:
Research, Commercial Applications
Applications:
Chatbots, Text Summarization
Primary Use Cases:
Long context processing, Instruction following
Limitations:
Extreme long context lengths may still pose challenges
Supported Languages 
en (High proficiency), zh (High proficiency)
Training Details 
Data Sources:
THUDM/LongAlign-10k
Data Volume:
10,000 long instructions (8k-64k length)
Methodology:
Long context training with packing and sorted batching
Context Length:
64000
Training Time:
Unknown
Model Architecture:
Extended context LLM architecture
Input Output 
Input Format:
Text prompts
Accepted Modalities:
Text
Output Format:
Generated text responses
Performance Tips:
Utilize appropriate context length settings for optimal performance
LLM NameLongAlign 6B 64K
Repository 🤗https://huggingface.co/THUDM/LongAlign-6B-64k 
Model Size6b
Required VRAM12.5 GB
Updated2025-02-22
MaintainerTHUDM
Model Typechatglm
Model Files  10.0 GB: 1-of-2   2.5 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureChatGLMForConditionalGeneration
Licenseapache-2.0
Transformers Version4.33.0
Tokenizer ClassChatGLMTokenizer
Vocabulary Size65024
Torch Data Typebfloat16

Best Alternatives to LongAlign 6B 64K

Best Alternatives
Context / RAM
Downloads
Likes
ChatGLM3 6B Theresa0K / 12.5 GB91
LongAlign 6B 64K Base0K / 12.3 GB285
Note: green Score (e.g. "73.2") means that the model is better than THUDM/LongAlign-6B-64k.

Rank the LongAlign 6B 64K 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? 43470 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 v20241227
  Support LLM Explorer