Autotrain compatible Dataset:linksoul/chinese-llava... En Endpoints compatible Instruct Llava Pytorch Region:us Sharded Vision Zh
Model Card on HF 🤗: https://huggingface.co/LinkSoul/Chinese-LLaVA-Cllama2
Chinese LLaVA Cllama2 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)
Chinese LLaVA Cllama2 Parameters and Internals
| Model Type |
| |||
| Use Cases |
| |||
| Additional Notes |
| |||
| Supported Languages |
| |||
| Input Output |
|
| LLM Name | Chinese LLaVA Cllama2 |
| Repository 🤗 | https://huggingface.co/LinkSoul/Chinese-LLaVA-Cllama2 |
| Required VRAM | 27 GB |
| Updated | 2025-02-22 |
| Maintainer | LinkSoul |
| Model Type | llava |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | zh en |
| Model Architecture | LlavaLlamaForCausalLM |
| License | openrail |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.28.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32003 |
| Torch Data Type | float32 |
Best Alternatives to Chinese LLaVA Cllama2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ConvLLaVA Sft 768 | 4K / 14.9 GB | 25 | 1 |
| ConvLLaVA Sft 1536 | 4K / 14.9 GB | 12 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than LinkSoul/Chinese-LLaVA-Cllama2 .
Rank the Chinese LLaVA Cllama2 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227