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

Paligemma Vqav2 by mervinpraison

 »  All LLMs  »  mervinpraison  »  Paligemma Vqav2   URL Share it on

  5   
  Adapter Base model:adapter:google/pali... Base model:google/paligemma-3b...   Dataset:vq av2   Finetuned   Generated from trainer   Lora   Peft   Region:us   Safetensors   Tensorboard
Model Card on HF 🤗: https://huggingface.co/mervinpraison/paligemma_vqav2 

Paligemma Vqav2 Benchmarks

LLME Score: 0.154
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Paligemma Vqav2 (mervinpraison/paligemma_vqav2)
🌟 Advertise your project 🚀

Paligemma Vqav2 Parameters and Internals

Additional Notes 
Training hyperparameters include learning_rate of 2e-05, train_batch_size of 8, eval_batch_size of 32, seed of 42, gradient_accumulation_steps of 8, total_train_batch_size of 64, optimizer as Adam with betas=(0.9,0.999) and epsilon=1e-08, lr_scheduler_type as linear, lr_scheduler_warmup_steps of 2, and num_epochs of 2.
Training Details 
Data Sources:
vq_av2
LLM NamePaligemma Vqav2
Repository 🤗https://huggingface.co/mervinpraison/paligemma_vqav2 
Base Model(s)  google/paligemma-3b-pt-224   google/paligemma-3b-pt-224
Model Size3b
Required VRAM0 GB
Updated2025-09-17
Maintainermervinpraison
Model Files  0.0 GB   0.0 GB
Model ArchitectureAdapter
Licensegemma
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|k_proj|up_proj|q_proj|down_proj|o_proj|gate_proj
LoRA Alpha8
LoRA Dropout0
R Param8

Best Alternatives to Paligemma Vqav2

Best Alternatives
Context / RAM
Downloads
Likes
Art Skynet 3B0K / 6.5 GB1115
...ull Lr5e4 Peft Mlp 32 32 Bs2560K / 0.7 GB50
Xenith 3B0K / 7.6 GB22
Results0K / 0.9 GB150
Accel30K / 0 GB50
Accel20K / 6.8 GB50
Openllama Test10K / 0.1 GB50
Paligemma Hindi0K / 2.2 GB50
Theory Of Mind 128 StableLM0K / 0.7 GB150
Theory Of Mind RP 128 StableLM0K / 0 GB50
Note: green Score (e.g. "73.2") means that the model is better than mervinpraison/paligemma_vqav2.

Rank the Paligemma Vqav2 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? 51567 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