Releases: huggingface/tei-gaudi
v1.5.2: SynapseAI v1.19.0
You can pull the Docker image associated to this release with:
docker pull ghcr.io/huggingface/tei-gaudi:1.5.2
SynapseAI v1.19.0
The codebase is validated with SynapseAI 1.19.0 and optimum-habana 1.15.0.
Validated Models
Text Embeddings
tei-gaudi
currently supports Nomic, BERT, CamemBERT, XLM-RoBERTa models with absolute positions, JinaBERT model with Alibi positions and Mistral, Alibaba GTE and Qwen2 models with Rope positions.
Below are some examples of our validated models:
Architecture | Pooling | Models |
---|---|---|
BERT | Cls/Mean/Last token | |
BERT | Splade | |
MPNet | Cls/Mean/Last token | |
ALBERT | Cls/Mean/Last token | |
Mistral | Cls/Mean/Last token | |
GTE | Cls/Mean/Last token | |
JinaBERT | Cls/Mean/Last token |
Sequence Classification and Re-Ranking
tei-gaudi
currently supports CamemBERT, and XLM-RoBERTa Sequence Classification models with absolute positions.
Below are some examples of the currently supported models:
Task | Model Type | Model ID |
---|---|---|
Re-Ranking | XLM-RoBERTa | BAAI/bge-reranker-large |
Re-Ranking | XLM-RoBERTa | BAAI/bge-reranker-base |
Sentiment Analysis | RoBERTa | SamLowe/roberta-base-go_emotions |
Full Changelog: huggingface/tgi-gaudi@v1.5.1...v1.5.2
v1.5.1: SynapseAI v1.18.0
You can pull the Docker image associated to this release with:
docker pull ghcr.io/huggingface/tei-gaudi:1.5.1
SynapseAI v1.18.0
The codebase is validated with SynapseAI 1.18.0 and optimum-habana 1.14.1.
Validated Models
Architecture | Model Type | Models |
---|---|---|
BERT | Embedding | |
MPNet | Embedding | |
ALBERT | Embedding | |
Mistral | Embedding | |
GTE | Embedding | |
JinaBERT | Embedding | |
Roberta | Sequence Classification |
Full Changelog: huggingface/tgi-gaudi@v1.5.0...v1.5.1
v1.5.0: SynapseAI v1.17.0
SynapseAI v1.17.0
The codebase is validated with SynapseAI 1.17.0 and optimum-habana 1.13.1.