Finetuned Gemma3 by Eya0910

 ยป  All LLMs  ยป  Eya0910  ยป  Finetuned Gemma3   URL Share it on

  Arxiv:1910.09700   Adapter Base model:adapter:google/gemm... Base model:google/gemma-1.1-2b...   Finetuned   Gemma   Lora   Peft   Region:us   Safetensors   Sharded   Tensorflow

Finetuned Gemma3 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Finetuned Gemma3 Parameters and Internals

LLM NameFinetuned Gemma3
Repository ๐Ÿค—https://huggingface.co/Eya0910/finetuned-gemma3 
Base Model(s)  google/gemma-1.1-2b-it   google/gemma-1.1-2b-it
Model Size2b
Required VRAM5.1 GB
Updated2024-08-20
MaintainerEya0910
Model Typegemma
Model Files  0.0 GB   5.0 GB: 1-of-2   0.1 GB: 2-of-2   0.0 GB   0.0 GB   0.0 GB
Model ArchitectureAdapter
Context Length8192
Model Max Length8192
Transformers Version4.38.0
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleso_proj|k_proj|gate_proj|q_proj|v_proj|up_proj|down_proj
LoRA Alpha8
LoRA Dropout0.05
R Param8
Torch Data Typefloat16
Finetuned Gemma3 (Eya0910/finetuned-gemma3)

Best Alternatives to Finetuned Gemma3

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2 2B It Ud0K / 0 GB422
Phi Gemma Nlaf V10K / 0.1 GB60
Phi Gemma Nlaf V00K / 0.1 GB50
Gemma 2B It Nlai P10K / 0 GB50
1 8K Adater Ger0K / 0 GB80
German 2B Lora 6K0K / 0 GB80
Ger Lora 3K Checkpoint0K / 0 GB80
2B Lora Adapter Llama Alpaca0K / 0.1 GB70
Google Gemma 2B 17198825710K / 0 GB60
Google Gemma 2B 17198986620K / 0 GB60
Note: green Score (e.g. "73.2") means that the model is better than Eya0910/finetuned-gemma3.

Rank the Finetuned Gemma3 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? 36026 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803