Llava V1.5 13B 4GB 8bit 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 V1.5 13B 4GB 8bit Parameters and Internals
| LLM Name | Llava V1.5 13B 4GB 8bit |
| Repository 🤗 | https://huggingface.co/4bit/llava-v1.5-13b-4GB-8bit |
| Model Size | 13b |
| Required VRAM | 14.1 GB |
| Updated | 2024-10-18 |
| Maintainer | 4bit |
| Model Type | llava |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | LlavaLlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llava V1.5 13B 4GB 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llava V1.5 13B EXL2 | 4K / 13.2 GB | 2 | 1 |
| Llava 13B V1.1 4bit 128g | 2K / 7.5 GB | 4 | 2 |
| Llava V1.5 13B | 4K / 26 GB | 314369 | 474 |
| Llava V1.6 Vicuna 13B | 4K / 26.7 GB | 16637 | 47 |
| Table Llava V1.5 13B | 4K / 26.6 GB | 22 | 1 |
| Evalalign V1.0 13B | 4K / 26.7 GB | 2 | 1 |
| Peenoblanc 52 Llava | 4K / 26.7 GB | 5 | 0 |
| Otterchecker | 4K / 26.7 GB | 6 | 2 |
| Llava 13B Custom | 4K / 26.7 GB | 5 | 0 |
| V Mllm 13B | 4K / 26.6 GB | 15 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than 4bit/llava-v1.5-13b-4GB-8bit .
Rank the Llava V1.5 13B 4GB 8bit 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803