Text Retrieval
Transformers
Safetensors
bidirectional_pplx_qwen3
feature-extraction
sentence-embeddings
contextual-embeddings
custom_code
Instructions to use seslami-pplx/pplx-embed-context-v1.2-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seslami-pplx/pplx-embed-context-v1.2-4B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("seslami-pplx/pplx-embed-context-v1.2-4B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
File size: 152 Bytes
43188fa | 1 2 3 4 5 6 | from transformers.models.qwen3.configuration_qwen3 import Qwen3Config
class PPLXQwen3Config(Qwen3Config):
model_type = "bidirectional_pplx_qwen3"
|