Autotrain compatible Custom code Dataset:freedomintelligence/al... Dataset:liuhaotian/llava-cc3m-... Dataset:liuhaotian/llava-instr... Dataset:shareai/sharegpt-chine... En Instruct Qh 360vl Region:us Safetensors Sharded Tensorflow Visual-question-answering Zh
Model Card on HF 🤗: https://huggingface.co/qihoo360/360VL-8B
360VL 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)
360VL 8B Parameters and Internals
| LLM Name | 360VL 8B |
| Repository 🤗 | https://huggingface.co/qihoo360/360VL-8B |
| Model Size | 8b |
| Required VRAM | 16.8 GB |
| Updated | 2025-02-22 |
| Maintainer | qihoo360 |
| Model Type | QH_360VL |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | zh en |
| Model Architecture | QH360_VL_LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Rank the 360VL 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227