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

LongCite Llama3.1 8B by THUDM

 »  All LLMs  »  THUDM  »  LongCite Llama3.1 8B   URL Share it on

  664   
  Arxiv:2409.02897   Autotrain compatible   Chatglm   Custom code   Dataset:thudm/longcite-45k   En   Endpoints compatible   Llama   Long context   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/THUDM/LongCite-llama3.1-8b 

LongCite Llama3.1 8B Benchmarks

LLME Score: 0.2313
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LongCite Llama3.1 8B (THUDM/LongCite-llama3.1-8b)

LongCite Llama3.1 8B Parameters and Internals

Model Type 
text generation
Use Cases 
Applications:
long-context question answering
Additional Notes 
The model supports generating fine-grained citations in long-context scenarios.
Supported Languages 
en (full), zh (partial)
Training Details 
Data Sources:
THUDM/LongCite-45k
Context Length:
128000
Model Architecture:
Llama
Input Output 
Input Format:
context and query
Accepted Modalities:
text
Output Format:
structured response with citations
LLM NameLongCite Llama3.1 8B
Repository 🤗https://huggingface.co/THUDM/LongCite-llama3.1-8b 
Model Size8b
Required VRAM16.1 GB
Updated2025-03-25
MaintainerTHUDM
Model Typellama
Model Files  3.5 GB: 0-of-5   3.5 GB: 1-of-5   3.5 GB: 2-of-5   3.5 GB: 3-of-5   2.1 GB: 4-of-5
Supported Languagesen zh
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.43.0.dev0
Tokenizer ClassTikTokenizer
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to LongCite Llama3.1 8B

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB5220681
A81024K / 16.1 GB2840
A21024K / 16.1 GB3630
A41024K / 16.1 GB3050
A61024K / 16.1 GB4400
A181024K / 16.1 GB2720
A11024K / 16.1 GB3430
A101024K / 16.1 GB3030
A121024K / 16.1 GB2560
C311024K / 16.1 GB1830
Note: green Score (e.g. "73.2") means that the model is better than THUDM/LongCite-llama3.1-8b.

Rank the LongCite Llama3.1 8B 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? 45595 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