Gemma 2B Gptq 8bit by vessl

 ยป  All LLMs  ยป  vessl  ยป  Gemma 2B Gptq 8bit   URL Share it on

  Arxiv:1910.09700   8-bit   8bit   Autotrain compatible   Endpoints compatible   Gemma   Gptq   Quantized   Region:us   Safetensors

Gemma 2B Gptq 8bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2B Gptq 8bit (vessl/gemma-2b-gptq-8bit)

Gemma 2B Gptq 8bit Parameters and Internals

LLM NameGemma 2B Gptq 8bit
Repository ๐Ÿค—https://huggingface.co/vessl/gemma-2b-gptq-8bit 
Model Size2b
Required VRAM3.1 GB
Updated2024-12-22
Maintainervessl
Model Typegemma
Model Files  3.1 GB
GPTQ QuantizationYes
Quantization Typegptq|8bit
Model ArchitectureGemmaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Gemma 2B Gptq 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 1.1 2B It GPTQ8K / 3.1 GB264751
Gemma 2B Gptq 4bit8K / 2.1 GB190
Gemma 2B GPTQ8K / 2.1 GB13891
CodeGemma 2B GPTQ8K / 3.1 GB141
Vi Gemma 2B RAG8K / 5.1 GB89113
... 2B It Hermes Function Calling8K / 5.1 GB210
Gemma 2B Bnb 4bit8K / 2.1 GB334015
Gemma 1.1 2B It Bnb 4bit8K / 2.1 GB12654
Gemma 2B It Bnb 4bit8K / 2.1 GB186918
My AwesomeFinance Model8K / 2.1 GB130
Note: green Score (e.g. "73.2") means that the model is better than vessl/gemma-2b-gptq-8bit.

Rank the Gemma 2B Gptq 8bit 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217