MiniCPM 2B Sft Int4 by openbmb

 ยป  All LLMs  ยป  openbmb  ยป  MiniCPM 2B Sft Int4   URL Share it on

  4-bit   Autotrain compatible   Conversational   Custom code   Gptq   Region:us   Safetensors

MiniCPM 2B Sft Int4 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 Sft Int4 (openbmb/MiniCPM-2B-sft-int4)

MiniCPM 2B Sft Int4 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Healthcare, Finance, Education
Applications:
Chatbots, Automated content generation, Customer support
Primary Use Cases:
Conversational agents, Content creation tools
Limitations:
Not suitable for legal or medical decision making
Considerations:
Always require human oversight.
Additional Notes 
Subject to rate limits and usage policies.
Supported Languages 
English (Advanced), French (Intermediate), Spanish (Intermediate), German (Beginner)
Training Details 
Data Sources:
BooksCorpus, Common Crawl, Wikipedia
Data Volume:
570GB of filtered text
Methodology:
Transformer architecture with attention mechanisms
Context Length:
2048
Training Time:
Several months using state-of-the-art hardware
Hardware Used:
256 GPUs for parallel training
Model Architecture:
Layered Transformer with self-attention blocks
Safety Evaluation 
Methodologies:
Red-teaming, Bias analysis
Findings:
Model exhibits biases based on data used
Risk Categories:
Misinformation, Bias
Ethical Considerations:
Ensuring responsible deployment considering societal impact.
Responsible Ai Considerations 
Fairness:
Bias mitigation techniques integrated.
Transparency:
Limited explainability due to complex architecture.
Accountability:
OpenAI responsible for model performance via API.
Mitigation Strategies:
Continuous monitoring of outputs.
Input Output 
Input Format:
Text prompt
Accepted Modalities:
text
Output Format:
Generated text in natural language
Performance Tips:
Short and clear prompts yield better results.
Release Notes 
Version:
3.0
Date:
2020-05-28
Notes:
Initial public release with improved language capabilities.
LLM NameMiniCPM 2B Sft Int4
Repository ๐Ÿค—https://huggingface.co/openbmb/MiniCPM-2B-sft-int4 
Model Size2b
Required VRAM2.5 GB
Updated2025-01-24
Maintaineropenbmb
Model Files  2.5 GB
Model ArchitectureMiniCPMForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size122753
Torch Data Typefloat16

Best Alternatives to MiniCPM 2B Sft Int4

Best Alternatives
Context / RAM
Downloads
Likes
MiniCPM 2B 128K64K / 6 GB41442
MiniCPM 2B Sft Fp324K / 10.9 GB4295295
MiniCPM 2B Sft Bf164K / 5.5 GB7902118
...iCPM 2B RAFT Lora Hotpotqa Dev4K / 5.5 GB270
MiniCPM Duplex4K / 5.5 GB232
MiniCPM MoE 8x2B4K / 27.7 GB11440
...iniCPM 2B DPO Fp32 Safetensors4K / 10.9 GB81
...iniCPM 2B DPO Bf16 Safetensors4K / 5.5 GB71
...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 openbmb/MiniCPM-2B-sft-int4.

Rank the MiniCPM 2B Sft Int4 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? 41817 in total.

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