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

Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed by PrunaAI

 »  All LLMs  »  PrunaAI  »  Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed   URL Share it on

  6   
  4-bit   4bit Base model:cognitivecomputatio... Base model:quantized:cognitive...   Bitsandbytes   Custom code   Phi-msft   Pruna-ai   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2_6-phi-2-bnb-4bit-smashed 

Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed Benchmarks

LLME Score: 0.16084
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed (PrunaAI/cognitivecomputations-dolphin-2_6-phi-2-bnb-4bit-smashed)
🌟 Advertise your project 🚀

Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed Parameters and Internals

Model Type 
smashed, compressed
Use Cases 
Areas:
commercial applications, research
Limitations:
Efficiency results may vary in other settings like different hardware or batch size., The model quality might vary from the base model.
Considerations:
We recommend testing efficiency gains directly in your use-cases.
Input Output 
Input Format:
Text prompt input
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Run the model under use-case conditions to assess efficiency gains. Check 'first' and 'Sync'/'Async' metrics for specific contexts.
LLM NameCognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2_6-phi-2-bnb-4bit-smashed 
Base Model(s)  Dolphin 2 6 Phi 2   cognitivecomputations/dolphin-2_6-phi-2
Model Size1.6b
Required VRAM1.9 GB
Updated2025-09-23
MaintainerPrunaAI
Model Typephi-msft
Model Files  1.9 GB
Quantization Type4bit
Model ArchitecturePhiForCausalLM
Model Max Length2048
Transformers Version4.40.0
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
Vocabulary Size51200
Torch Data Typefloat16
Activation Functiongelu_new

Best Alternatives to Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Qlora4b Phi2K / 2.5 GB140
Qlora4b DPO2K / 2.5 GB130
...reamtobenlpsama Mcqa Quantized2K / 1.8 GB60
TeachersHateChatbotsMCQ Mini2K / 2.4 GB60
Qlora4b DPO2K / 2.5 GB60
Qlora4b Phi2K / 2.5 GB60
Phi2 Spelling2K / 1.8 GB60
Phi 2 Voicechange2K / 2.5 GB70
Phi2 Changevoice2K / 2.4 GB60
Phi 2 Maths2K / 1.9 GB62

Rank the Cognitivecomputations Dolphin 2 6 Phi 2 Bnb 4bit Smashed 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? 51544 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 v20241124
  Support LLM Explorer