Gemma 2B It Sft by date3k2

 ยป  All LLMs  ยป  date3k2  ยป  Gemma 2B It Sft   URL Share it on

  Adapter Base model:adapter:google/gemm... Base model:google/gemma-1.1-2b...   Conversational   Finetuned   Generated from trainer   Lora   Peft   Region:us   Safetensors   Sft   Trl   Vi
Model Card on HF ๐Ÿค—: https://huggingface.co/date3k2/gemma-2b-it-sft 

Gemma 2B It Sft 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 It Sft (date3k2/gemma-2b-it-sft)

Gemma 2B It Sft Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model trained with specific hyperparameters: learning_rate: 0.0002, train_batch_size: 4, eval_batch_size: 8, optimizer: Adam with betas=(0.9,0.999), and a linear lr_scheduler.
Supported Languages 
vi (Vietnamese)
LLM NameGemma 2B It Sft
Repository ๐Ÿค—https://huggingface.co/date3k2/gemma-2b-it-sft 
Base Model(s)  google/gemma-1.1-2b-it   google/gemma-1.1-2b-it
Model Size2b
Required VRAM0.3 GB
Updated2024-11-27
Maintainerdate3k2
Model Files  0.3 GB   0.0 GB
Supported Languagesvi
Model ArchitectureAdapter
Licensegemma
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<eos>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|down_proj|v_proj|q_proj|up_proj|o_proj|k_proj
LoRA Alpha16
LoRA Dropout0.1
R Param64

Best Alternatives to Gemma 2B It Sft

Best Alternatives
Context / RAM
Downloads
Likes
Finetuned Gemma38K / 5.1 GB90
Phi Gemma Nlaf V10K / 0.1 GB50
Phi Gemma Nlaf V00K / 0.1 GB50
Gemma 2B It Nlai P10K / 0 GB60
Ger Lora 3K Checkpoint0K / 0 GB80
German 2B Lora 6K0K / 0 GB60
1 8K Adater Ger0K / 0 GB50
2B Lora Adapter Llama Alpaca0K / 0.1 GB70
Google Gemma 2B 17198825710K / 0 GB70
Google Gemma 2B 17198986620K / 0 GB60
Note: green Score (e.g. "73.2") means that the model is better than date3k2/gemma-2b-it-sft.

Rank the Gemma 2B It Sft 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? 43470 in total.

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