Customized Further Fine-Tuning by Users
#15 opened 12 days ago
by
fwj
Model keeps cache of generation in Transformers (fixed using torch.no_grad())
#14 opened 13 days ago
by
Pietroferr
gte-Qwen2-1.5B-instruct模型半精度推理时,模型输出结果NAN
#13 opened 14 days ago
by
Erin
Qwen 2.5 1.5B retrain?
4
#12 opened 22 days ago
by
tomaarsen
mteb 测试速度问题
2
#10 opened 30 days ago
by
xiaopli11
Support of Xformer and FlashAttnention
1
#9 opened 2 months ago
by
le723z
ONNX.data
#8 opened 2 months ago
by
Saugatkafley
Fine-tunning
#5 opened 3 months ago
by
deleted
sequence classification
1
#3 opened 3 months ago
by
prudant
score mteb french
2
#2 opened 3 months ago
by
abhamadi
"Bidirectional attention"
2
#1 opened 3 months ago
by
olivierdehaene