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 Llama Format by openbmb

 »  All LLMs  »  openbmb  »  MiniCPM 2B DPO Bf16 Llama Format   URL Share it on

  130   
  Autotrain compatible   Conversational   En   Endpoints compatible   Llama   Minicpm   Modelbest   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Thunlp   Zh
Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16-llama-format 

MiniCPM 2B DPO Bf16 Llama Format Benchmarks

LLME Score: 0.17067
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 Llama Format (openbmb/MiniCPM-2B-dpo-bf16-llama-format)

MiniCPM 2B DPO Bf16 Llama Format Parameters and Internals

Model Type 
language model, multimodal model
Use Cases 
Areas:
research, limited commercial applications
Primary Use Cases:
multimodal applications, language model tasks
Limitations:
hallucinations, affected by prompts, knowledge memory limitations
Considerations:
Use RAG method to enhance knowledge memory.
Additional Notes 
First multimodal model deployable on smartphones.
Supported Languages 
English (unknown), Chinese (unknown)
Training Details 
Data Sources:
ShareGPT, open-source corpus
Methodology:
SFT (Supervised Fine-Tuning), DPO (Draft Prompt Optimization)
Hardware Used:
GPU 1080/2080 for parameter efficient finetuning, GPU 3090/4090 for full parameter finetuning
Safety Evaluation 
Risk Categories:
hallucinatory issues
Responsible Ai Considerations 
Mitigation Strategies:
Continual iteration to improve model and mitigate hallucinations.
Input Output 
Input Format:
Supports both language and multimodal inputs.
Accepted Modalities:
text, multimodal
Output Format:
Textual outputs with multimodal capabilities.
Performance Tips:
Specify data type clearly in 'from_pretrained'.
LLM NameMiniCPM 2B DPO Bf16 Llama Format
Repository 🤗https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16-llama-format 
Model Size2b
Required VRAM10.9 GB
Updated2025-02-05
Maintaineropenbmb
Model Typellama
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   0.9 GB: 3-of-3   6.0 GB
Supported Languagesen zh
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size122753
Torch Data Typebfloat16

Best Alternatives to MiniCPM 2B DPO Bf16 Llama Format

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2B Hf 32768 Fpf32K / 3.8 GB1751
YuLan Mini28K / 4.8 GB32235
...icpm 2B Sft Bf16 Llamafied 16K16K / 6 GB5601
Salamandra 2B8K / 4.5 GB1027722
SmolLM2 MedIT Upscale 2B8K / 4.2 GB84
Salamandra 2B Instruct8K / 4.5 GB298918
Sarvam 2B V0.58K / 5.1 GB63483
Test Quantized8K / 5.8 GB760
EPFL TA Meister Quantized V18K / 5.8 GB780
Llama3 2B Base8K / 4.7 GB831
Note: green Score (e.g. "73.2") means that the model is better than openbmb/MiniCPM-2B-dpo-bf16-llama-format.

Rank the MiniCPM 2B DPO Bf16 Llama Format 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? 42577 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