Yuan2 M32 Hf by IEITYuan

 ยป  All LLMs  ยป  IEITYuan  ยป  Yuan2 M32 Hf   URL Share it on

  Arxiv:2405.17976   Autotrain compatible   Custom code   Pytorch   Region:us   Sharded   Yuan
Model Card on HF ๐Ÿค—: https://huggingface.co/IEITYuan/Yuan2-M32-hf 

Yuan2 M32 Hf Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yuan2 M32 Hf (IEITYuan/Yuan2-M32-hf)

Yuan2 M32 Hf Parameters and Internals

Model Type 
Mixture-of-Experts (MoE)
Use Cases 
Areas:
Research, Commercial applications
Applications:
Language understanding, Coding, Math reasoning
Primary Use Cases:
Mathematical computation, Code generation
Limitations:
Easily misled by input instructions
Considerations:
Comply with the license agreement.
Additional Notes 
Operates with 3.7B active parameters out of total 40B, using 7.4 GFLOPS per token.
Supported Languages 
English (Proficient), Chinese (Proficient)
Training Details 
Data Volume:
2000B tokens
Methodology:
Attention Router for expert selection
Context Length:
16000
Model Architecture:
Mixture-of-Experts with Attention Router
Input Output 
Input Format:
16K sequence length
Accepted Modalities:
text
Output Format:
Depends on task
LLM NameYuan2 M32 Hf
Repository ๐Ÿค—https://huggingface.co/IEITYuan/Yuan2-M32-hf 
Required VRAM79.8 GB
Updated2025-02-22
MaintainerIEITYuan
Model Typeyuan
Model Files  10.0 GB: 1-of-9   10.0 GB: 2-of-9   9.9 GB: 3-of-9   10.0 GB: 4-of-9   9.9 GB: 5-of-9   10.0 GB: 6-of-9   9.9 GB: 7-of-9   10.0 GB: 8-of-9   0.1 GB: 9-of-9
Model ArchitectureYuanForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.30.2
Tokenizer ClassYuanTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size135040
Torch Data Typebfloat16

Best Alternatives to Yuan2 M32 Hf

Best Alternatives
Context / RAM
Downloads
Likes
Yuan2 M324K /  GB234

Rank the Yuan2 M32 Hf 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227