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

MiniCPM 2B DPO Bf16 Safetensors by Goekdeniz-Guelmez

 »  All LLMs  »  Goekdeniz-Guelmez  »  MiniCPM 2B DPO Bf16 Safetensors   URL Share it on

  7   
  Custom code   En   Minicpm   Mlx   Modelbest   Region:us   Safetensors   Thunlp   Zh
Model Card on HF 🤗: https://huggingface.co/Goekdeniz-Guelmez/MiniCPM-2B-dpo-bf16-safetensors 

MiniCPM 2B DPO Bf16 Safetensors Benchmarks

LLME Score: 0.19505
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 Bf16 Safetensors (Goekdeniz-Guelmez/MiniCPM-2B-dpo-bf16-safetensors)

MiniCPM 2B DPO Bf16 Safetensors Parameters and Internals

Model Type 
Multimodal, Language Model
Use Cases 
Areas:
Academic Research, Commercial Applications (with authorization)
Applications:
Text Generation, Multimodal Inference
Primary Use Cases:
Language Processing, Model Deployment on Mobile Devices
Limitations:
Model can hallucinate due to its size limitations., Outputs are significantly influenced by prompts.
Considerations:
Users responsible for verifying outputs, particularly in sensitive use cases.
Additional Notes 
MiniCPM is open-source for academic use, with additional requirements for commercial use.
Supported Languages 
Chinese (High proficiency), English (High proficiency)
Training Details 
Data Sources:
Open-source corpus, ShareGPT
Methodology:
SFT and DPO
Hardware Used:
1080/2080 GPU, 3090/4090 GPU
Safety Evaluation 
Ethical Considerations:
The model does not understand or express personal opinions. Responsibility for evaluation and verification of content lies with the user.
Responsible Ai Considerations 
Fairness:
Model trained on a vast amount of open-source corpus to ensure wide adaptability.
Transparency:
Developers emphasize the model's inability to express opinions.
Accountability:
Users are responsible for evaluating and verifying the generated content.
Mitigation Strategies:
Iterative improvement plans for the model announced.
Input Output 
Input Format:
Text prompts
Accepted Modalities:
Text, Multimodal
Output Format:
Text responses
Performance Tips:
Specify model data types in 'from_pretrained' to avoid calculation errors.
LLM NameMiniCPM 2B DPO Bf16 Safetensors
Repository 🤗https://huggingface.co/Goekdeniz-Guelmez/MiniCPM-2B-dpo-bf16-safetensors 
Model Size2b
Required VRAM5.5 GB
Updated2024-12-21
MaintainerGoekdeniz-Guelmez
Model Typeminicpm
Model Files  5.5 GB
Supported Languagesen zh
Model ArchitectureMiniCPMForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size122753
Torch Data Typebfloat16

Best Alternatives to MiniCPM 2B DPO Bf16 Safetensors

Best Alternatives
Context / RAM
Downloads
Likes
MiniCPM 2B 128K64K / 6 GB66941
MiniCPM 2B Sft Fp324K / 10.9 GB4216295
MiniCPM 2B Sft Bf164K / 5.5 GB8362118
MiniCPM MoE 8x2B4K / 27.7 GB49240
...iCPM 2B RAFT Lora Hotpotqa Dev4K / 5.5 GB90
MiniCPM Duplex4K / 5.5 GB132
MiniCPM 2B DPO Bf164K / 5.5 GB69347
...iniCPM 2B DPO Fp32 Safetensors4K / 10.9 GB111
...iniCPM 2B Sft Fp32 Safetensors4K / 10.9 GB71
...iniCPM 2B Sft Fp32 Safetensors4K / 10.9 GB61
Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/MiniCPM-2B-dpo-bf16-safetensors.

Rank the MiniCPM 2B DPO Bf16 Safetensors 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? 40013 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 v20241217
  Support LLM Explorer