MiniCPM 2B DPO Fp32 by openbmb

 ยป  All LLMs  ยป  openbmb  ยป  MiniCPM 2B DPO Fp32   URL Share it on

  Autotrain compatible   Conversational   Custom code   En   Minicpm   Modelbest   Pytorch   Region:us   Thunlp   Zh

MiniCPM 2B DPO Fp32 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiniCPM 2B DPO Fp32 (openbmb/MiniCPM-2B-dpo-fp32)

MiniCPM 2B DPO Fp32 Parameters and Internals

Model Type 
End-size LLM, Multimodal
Use Cases 
Areas:
Research, Commercial applications
Applications:
Multimodal model deployment, Smartphone inference
Primary Use Cases:
End-size language model applications
Limitations:
Model size limitations leading to hallucination issues, Influence of prompt words leading to inconsistent results, Inaccurate knowledge memory due to limited capacity
Additional Notes 
MiniCPM models and weights are fully open for research and limited commercial use pending registration.
Training Details 
Data Sources:
ShareGPT open-source corpus
Methodology:
SFT and DPO techniques applied
Input Output 
Accepted Modalities:
Text, Multimodal inputs
Performance Tips:
Clear data type specification in 'from_pretrained' to avoid large calculation errors
LLM NameMiniCPM 2B DPO Fp32
Repository ๐Ÿค—https://huggingface.co/openbmb/MiniCPM-2B-dpo-fp32 
Model Size2b
Required VRAM10.9 GB
Updated2025-02-05
Maintaineropenbmb
Model Files  10.9 GB
Supported Languagesen zh
Model ArchitectureMiniCPMForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size122753
Torch Data Typefloat32

Quantized Models of the MiniCPM 2B DPO Fp32

Model
Likes
Downloads
VRAM
MiniCPM 2B DPO Fp16341655 GB

Best Alternatives to MiniCPM 2B DPO Fp32

Best Alternatives
Context / RAM
Downloads
Likes
MiniCPM 2B 128K64K / 6 GB29442
Sparsing Law 0.1B Relu4K / 0.4 GB1481
MiniCPM 2B Sft Fp324K / 10.9 GB3636296
MiniCPM 2B Sft Bf164K / 5.5 GB8436118
...iCPM 2B RAFT Lora Hotpotqa Dev4K / 5.5 GB70
MiniCPM Duplex4K / 5.5 GB92
MiniCPM MoE 8x2B4K / 27.7 GB8040
...iniCPM 2B DPO Fp32 Safetensors4K / 10.9 GB81
...iniCPM 2B DPO Bf16 Safetensors4K / 5.5 GB71
...iniCPM 2B Sft Fp32 Safetensors4K / 10.9 GB71
Note: green Score (e.g. "73.2") means that the model is better than openbmb/MiniCPM-2B-dpo-fp32.

Rank the MiniCPM 2B DPO Fp32 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? 42577 in total.

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