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 2.8 Gemma 2B Bnb 4bit Smashed by PrunaAI

 »  All LLMs  »  PrunaAI  »  Cognitivecomputations Dolphin 2.8 Gemma 2B Bnb 4bit Smashed   URL Share it on

  23   
  4-bit   4bit   Autotrain compatible Base model:cognitivecomputatio... Base model:quantized:cognitive...   Bitsandbytes   Conversational   Endpoints compatible   Gemma   Pruna-ai   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-bnb-4bit-smashed 

Cognitivecomputations Dolphin 2.8 Gemma 2B Bnb 4bit Smashed Benchmarks

LLME Score: 0.20157
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cognitivecomputations Dolphin 2.8 Gemma 2B Bnb 4bit Smashed (PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-bnb-4bit-smashed)

Cognitivecomputations Dolphin 2.8 Gemma 2B Bnb 4bit Smashed Parameters and Internals

Model Type 
causal_language_model
Use Cases 
Primary Use Cases:
compression for cheaper, smaller, faster, greener AI models
Limitations:
Comparison results may vary depending on hardware, image size, batch size
Considerations:
Efficiency should be tested directly in use-case conditions.
Training Details 
Data Sources:
WikiText
Methodology:
llm-int8
Input Output 
Input Format:
Expected input in the form of text sequences tokenized using tokenizer.
Accepted Modalities:
text
Output Format:
Generates text sequences as output tokens.
Performance Tips:
Test the efficiency gains directly in your use-cases.
LLM NameCognitivecomputations Dolphin 2.8 Gemma 2B Bnb 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-bnb-4bit-smashed 
Base Model(s)  cognitivecomputations/dolphin-2.8-gemma-2b   cognitivecomputations/dolphin-2.8-gemma-2b
Model Size2b
Required VRAM2.2 GB
Updated2025-01-15
MaintainerPrunaAI
Model Typegemma
Model Files  2.2 GB
Quantization Type4bit
Model ArchitectureGemmaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Cognitivecomputations Dolphin 2.8 Gemma 2B Bnb 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Vi Gemma 2B RAG8K / 5.1 GB51513
... 2B It Hermes Function Calling8K / 5.1 GB100
Gemma 1.1 2B It Bnb 4bit8K / 2.1 GB14334
Gemma 2B Bnb 4bit8K / 2.1 GB269915
Jenna V28K / 5.1 GB1190
My AwesomeFinance Model8K / 2.1 GB210
Test Model8K / 2.1 GB960
... 2.8 Gemma 2B HQQ 1bit Smashed8K / 1.3 GB170
... 2.8 Gemma 2B HQQ 2bit Smashed8K / 1.6 GB170
... 2.8 Gemma 2B HQQ 4bit Smashed8K / 2.1 GB170
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-bnb-4bit-smashed.

Rank the Cognitivecomputations Dolphin 2.8 Gemma 2B 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? 41418 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