MiniCPM 2B Sft Fp32 Safetensors by Isaak-Carter

 »  All LLMs  »  Isaak-Carter  »  MiniCPM 2B Sft Fp32 Safetensors   URL Share it on

  Custom code   En   Minicpm   Mlx   Modelbest   Region:us   Safetensors   Thunlp   Zh

MiniCPM 2B Sft Fp32 Safetensors 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 Fp32 Safetensors (Isaak-Carter/MiniCPM-2B-sft-fp32-safetensors)

MiniCPM 2B Sft Fp32 Safetensors Parameters and Internals

Model Type 
End-Size Large Language Model, Multimodal Model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Multimodal Models
Limitations:
Hallucination issues due to model size, Identity information similar to GPT due to ShareGPT data, Prompt sensitivity affecting consistency, Knowledge memory inaccuracies
Considerations:
No identity-specific training conducted
Additional Notes 
Model stream outputs are faster than human verbal speed, can deploy on smartphones.
Supported Languages 
Chinese (High proficiency), English (Moderate proficiency)
Training Details 
Data Sources:
Open source corpus including ShareGPT
Methodology:
SFT (Supervised Fine Tuning) and DPO (Decentralized Proof of Output)
Hardware Used:
GPU 1080/2080 for efficient tuning, GPU 3090/4090 for full param tuning
LLM NameMiniCPM 2B Sft Fp32 Safetensors
Repository 🤗https://huggingface.co/Isaak-Carter/MiniCPM-2B-sft-fp32-safetensors 
Model Size2b
Required VRAM10.9 GB
Updated2024-09-21
MaintainerIsaak-Carter
Model Typeminicpm
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

Best Alternatives to MiniCPM 2B Sft Fp32 Safetensors

Best Alternatives
Context / RAM
Downloads
Likes
MiniCPM 2B 128K64K / 6 GB44241
MiniCPM 2B Sft Fp324K / 10.9 GB2654295
MiniCPM 2B Sft Bf164K / 5.5 GB7100118
...iCPM 2B RAFT Lora Hotpotqa Dev4K / 5.5 GB280
MiniCPM MoE 8x2B4K / 27.7 GB26540
MiniCPM Duplex4K / 5.5 GB262
...iniCPM 2B DPO Fp32 Safetensors4K / 10.9 GB101
...iniCPM 2B DPO Bf16 Safetensors4K / 5.5 GB71
...iniCPM 2B Sft Fp32 Safetensors4K / 10.9 GB61
...iniCPM 2B DPO Bf16 Safetensors4K / 5.5 GB11
Note: green Score (e.g. "73.2") means that the model is better than Isaak-Carter/MiniCPM-2B-sft-fp32-safetensors.

Rank the MiniCPM 2B Sft Fp32 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? 40918 in total.

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