Arxiv:2311.10122 Arxiv:2401.15947 Autotrain compatible Custom code Endpoints compatible Moe Moe llava phi Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LanguageBind/MoE-LLaVA-Phi2-2.7B-4e
MoE LLaVA Phi2 2.7B 4e 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)
MoE LLaVA Phi2 2.7B 4e Parameters and Internals
| Model Type |
| |||||||||
| Additional Notes |
| |||||||||
| Training Details |
|
| LLM Name | MoE LLaVA Phi2 2.7B 4e |
| Repository 🤗 | https://huggingface.co/LanguageBind/MoE-LLaVA-Phi2-2.7B-4e |
| Model Size | 5.6b |
| Required VRAM | 11.2 GB |
| Updated | 2025-09-23 |
| Maintainer | LanguageBind |
| Model Type | moe_llava_phi |
| Model Files | |
| Model Architecture | MoELLaVAPhiForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|extra_0|> |
| Vocabulary Size | 51200 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to MoE LLaVA Phi2 2.7B 4e
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| DynMoE Phi 2 2.7B | 2K / 11.2 GB | 7 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than LanguageBind/MoE-LLaVA-Phi2-2.7B-4e .
Rank the MoE LLaVA Phi2 2.7B 4e 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? 51556 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124