Downloads · 30 days
3
6% of all-time downloads
Seraphic663/lrat-qwen3-0.6b-1epoch-20260716
lrat-qwen3-0.6b-1epoch-20260716 is a feature extraction model from Seraphic663. Use it when you need embeddings to search or compare text. It is set up for transformers.
This is a full-parameter retriever checkpoint based on Qwen/Qwen3-Embedding-0.6B, prepared for the CCIR LRAT competition.
Downloads · 30 days
3
6% of all-time downloads
All-time downloads
54
Public
Parameters
596M
2.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.4 GB · 99%
From the Hugging Face model README
This is a full-parameter retriever checkpoint based on
Qwen/Qwen3-Embedding-0.6B, prepared for the CCIR LRAT competition.
Given a web search query, retrieve relevant passages that answer the queryThe training objective uses LRAT reweight_rate values with cross-device
negatives. The checkpoint contains merged full model parameters and does not
require a LoRA or adapter at inference time.
import torch
import torch.nn.functional as F
from transformers import AutoModel, AutoTokenizer
model_id = "Seraphic663/lrat-qwen3-0.6b-1epoch-20260716"
tokenizer = AutoTokenizer.from_pretrained(model_id, padding_side="left")
model = AutoModel.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
).cuda().eval()
instruction = "Given a web search query, retrieve relevant passages that answer the query"
texts = [f"Instruct: {instruction}\nQuery:example query", "example passage"]
batch = tokenizer(texts, padding=True, truncation=True, max_length=512, return_tensors="pt").to("cuda")
with torch.inference_mode():
output = model(**batch).last_hidden_state
embeddings = F.normalize(output[:, -1].float(), p=2, dim=1)
On a fixed 500-row candidate-set development diagnostic, this checkpoint obtained Recall@1/5/10 of 0.672/0.934/0.984 and MRR of 0.78037. These are local candidate-set diagnostics, not official BC-Plus leaderboard scores.
model.safetensors
2,383,139,480 bytes
SHA-256 b25b3b08a3199a788ea5e8bc005ee20ab831ada36cb4eccd7ba915e0d6e02501