Model Card on HF 🤗: https://huggingface.co/adonlee/llava-6B
Llava 6B 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 6B Parameters and Internals
| LLM Name | Llava 6B |
| Repository 🤗 | https://huggingface.co/adonlee/llava-6B |
| Model Size | 6b |
| Required VRAM | 12.7 GB |
| Updated | 2025-02-07 |
| Maintainer | adonlee |
| Model Type | llava |
| Model Files | |
| Model Architecture | LlavaLlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.31.0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <|startoftext|> |
| End of Sentence Token | <|endoftext|> |
| Unk Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llava 6B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yi VL 6B | 4K / 13.4 GB | 118 | 124 |
| ...L Chat ViT 6B Vicuna 13B 448px | 4K / 37.9 GB | 45 | 4 |
| InternVL Chat ViT 6B Vicuna 7B | 4K / 25.4 GB | 80 | 8 |
| ...nternVL Chat ViT 6B Vicuna 13B | 4K / 37.9 GB | 47 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than adonlee/llava-6B .
Rank the Llava 6B 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