Desearch-Embedding-8B / sentence_bert_config.json

Desearch Embedding 8B: LoRA adapter on Qwen3-Embedding-8B, model card with /search A/B results

5bc4751 verified about 1 month ago

241 Bytes

{
    "transformer_task": "feature-extraction",
    "modality_config": {
        "text": {
            "method": "forward",
            "method_output_name": "last_hidden_state"
        }
    },
    "module_output_name": "token_embeddings"
}

	{
	"transformer_task": "feature-extraction",
	"modality_config": {
	"text": {
	"method": "forward",
	"method_output_name": "last_hidden_state"
	}
	},
	"module_output_name": "token_embeddings"
	}