Adapter Base model:adapter:google/pali... Base model:google/paligemma-3b... Finetuned Generated from trainer Lora Peft Region:us Safetensors Tensorboard
Model Card on HF 🤗: https://huggingface.co/damerajee/paligemma-hindi
Paligemma Hindi Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Paligemma Hindi Parameters and Internals
| LLM Name | Paligemma Hindi |
| Repository 🤗 | https://huggingface.co/damerajee/paligemma-hindi |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 2.2 GB |
| Updated | 2024-11-17 |
| Maintainer | damerajee |
| Model Files | |
| Model Architecture | Adapter |
| License | gemma |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|o_proj|v_proj|q_proj|k_proj|up_proj|down_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Paligemma Hindi
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Art Skynet 3B | 0K / 6.5 GB | 22 | 6 |
| ...ull Lr5e4 Peft Mlp 32 32 Bs256 | 0K / 0.7 GB | 6 | 0 |
| Xenith 3B | 0K / 7.6 GB | 2 | 2 |
| Results | 0K / 0.9 GB | 6 | 0 |
| Accel3 | 0K / 0 GB | 7 | 0 |
| Accel2 | 0K / 6.8 GB | 5 | 0 |
| Openllama Test1 | 0K / 0.1 GB | 5 | 0 |
| Paligemma Vqav2 | 0K / 0 GB | 5 | 0 |
| Theory Of Mind 128 StableLM | 0K / 0.7 GB | 6 | 0 |
| Theory Of Mind RP 128 StableLM | 0K / 0 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than damerajee/paligemma-hindi .
Rank the Paligemma Hindi 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! 🌟
What open-source LLMs or SLMs are you in search of? 42625 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227