Description
Pretrained E5Embeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.m_e5_base_v2_e_2_t_llama_index_pipeline is a None model originally trained by shrijayan.
How to use
pipeline = PretrainedPipeline("m_e5_base_v2_e_2_t_llama_index_pipeline", lang = "nan")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("m_e5_base_v2_e_2_t_llama_index_pipeline", lang = "nan")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | m_e5_base_v2_e_2_t_llama_index_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | nan |
| Size: | 385.3 MB |
References
https://huggingface.co/shrijayan/M-e5-base-v2_E-2_T-Llama.Index
Included Models
- DocumentAssembler
- E5Embeddings