Ar Autotrain compatible Bn De En Endpoints compatible Es Fr Id Ja Ko Qwen2 Region:us Ru Safetensors Sw Te Text-ranking Th Zh
Model Card on HF 🤗: https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v2
Mxbai Rerank Base V2 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)
Mxbai Rerank Base V2 Parameters and Internals
| LLM Name | Mxbai Rerank Base V2 |
| Repository 🤗 | https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v2 |
| Model Size | 494m |
| Required VRAM | 1 GB |
| Updated | 2025-04-30 |
| Maintainer | mixedbread-ai |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en zh de ja ko es fr ar bn ru id sw te th |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Mxbai Rerank Base V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Tinyqwen | 128K / 1 GB | 5 | 0 |
| TinySphinx2.0 | 32K / 1 GB | 25 | 0 |
Rank the Mxbai Rerank Base V2 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? 46860 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227