LLaVA Med Weights 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)
LLaVA Med Weights Parameters and Internals
| LLM Name | LLaVA Med Weights |
| Repository 🤗 | https://huggingface.co/sbottazziunsam/LLaVA-Med_weights |
| Required VRAM | 13.5 GB |
| Updated | 2024-09-07 |
| Maintainer | sbottazziunsam |
| Model Type | llava |
| Model Files | |
| Model Architecture | LlavaLlamaForCausalLM |
| Model Max Length | 1024 |
| Transformers Version | 4.28.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32004 |
| Torch Data Type | float16 |
Best Alternatives to LLaVA Med Weights
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ConvLLaVA Pretrain 1536 | 4K / 14.9 GB | 9 | 2 |
| ConvLLaVA Sft 1536 | 4K / 14.9 GB | 16 | 0 |
| ConvLLaVA Pretrain 768 | 4K / 14.9 GB | 7 | 1 |
| ConvLLaVA Sft 768 | 4K / 14.9 GB | 4 | 1 |
| Dermatology LLaVA | 4K / 14.7 GB | 23 | 0 |
| Uni MoE Speech Base Interval | 4K / 54.6 GB | 6 | 1 |
| Uni MoE Audio Base | 4K / 53.4 GB | 8 | 1 |
| Uni MoE Speech Base | 4K / 80.5 GB | 8 | 1 |
| Qilin Med VL Chat | 4K / 26 GB | 32 | 1 |
| Qilin Med VL | 4K / 26.6 GB | 8 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than sbottazziunsam/LLaVA-Med_weights .
Rank the LLaVA Med Weights 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803