LorMolf
/

Qwen-Embedding-ProcCode

Feature Extraction

text-generation

legal-retrieval

text-embeddings-inference

Model card Files Files and versions

LorMolf/Qwen-Embedding-ProcCode

Merged Qwen3-Embedding checkpoint for Italian public-procurement retrieval.

Base model: Qwen/Qwen3-Embedding-0.6B
Merge base model: src_appalti/src_retriever/data/qwen3_embedding/merged/qwen3-basecode-init-from-20260621-checkpoint-2000
Initialization adapter checkpoint: src_appalti/src_retriever/data/qwen3_embedding/outputs/qwen3-embedding-0_6b-phased-2k-b6-20260621_003550/v0-20260621-003640/checkpoint-2000
Adapter checkpoint: src_appalti/src_retriever/data/qwen3_embedding/outputs/qwen3-embedding-basecode-overnight-2k-20260621_204545/v0-20260621-204845/checkpoint-2000
Merge time: 2026-06-22T00:35:21.086999+00:00
Training backend: SWIFT qwen3_emb LoRA, InfoNCE
Expected query format: Instruct: <retrieval instruction>\nQuery: <question>
Document format: raw article/source or wiki-node text without instruction prefix
Max context used during training/eval: 32768 tokens

Downloads last month: 26

Safetensors

Model size

0.6B params

Tensor type

BF16

·

Model tree for LorMolf/Qwen-Embedding-ProcCode

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-Embedding-0.6B

Finetuned

(191)

this model