Autotrain compatible Dataset:liuhaotian/llava-instr... Dataset:liuhaotian/llava-pretr... En Endpoints compatible Instruct Llava llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/weizhiwang/LLaVA-Llama-3-8B
LLaVA Llama 3 8B 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 Llama 3 8B Parameters and Internals
| Model Type |
| ||||||||||
| Supported Languages |
| ||||||||||
| Input Output |
| ||||||||||
| Release Notes |
|
| LLM Name | LLaVA Llama 3 8B |
| Repository 🤗 | https://huggingface.co/weizhiwang/LLaVA-Llama-3-8B |
| Model Size | 8b |
| Required VRAM | 16.7 GB |
| Updated | 2025-09-23 |
| Maintainer | weizhiwang |
| Model Type | llava_llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlavaLlamaForCausalLM |
| License | cc |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_0|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to LLaVA Llama 3 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama3 Llava Next 8B | 8K / 16.7 GB | 3381 | 100 |
| Llava Llama 3 8B MultiModal V1 | 8K / 16.1 GB | 3 | 1 |
| LLaVA Video Llama 3 | 8K / 16.7 GB | 139 | 4 |
| LLaVA Meta Llama 3 8B Instruct | 8K / 16.7 GB | 35 | 12 |
| ...VA Meta Llama 3 8B Instruct FT | 8K / 16.7 GB | 7 | 12 |
| ...Meta Llama 3 8B Instruct FT S2 | 8K / 16.7 GB | 9 | 4 |
| Vip Llava Llama 3 8B | 8K / 16.8 GB | 6 | 0 |
| Llava 1.5 Llama 3 8B | 8K / 16.7 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than weizhiwang/LLaVA-Llama-3-8B .
Rank the LLaVA Llama 3 8B 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124