Dingkun Long
thenlper
AI & ML interests
Natural Language Processing; Information Retrieval
Organizations
thenlper's activity
FP32 or FP16
1
#20 opened 26 days ago
by
timbmg
how to export onnx format?
4
#12 opened about 2 months ago
by
nampham1106
Qwen 2.5 1.5B retrain?
4
#12 opened about 2 months ago
by
tomaarsen
Fix broken SentenceTransformer snippet; format code with Python format
#11 opened about 2 months ago
by
tomaarsen
use Flash Attention
3
#8 opened 3 months ago
by
kakascode
反问句的重排似乎效果不佳
1
#5 opened 3 months ago
by
bash99
某些特殊情况匹配排序会有错)
2
#5 opened 3 months ago
by
bash99
会考虑发布到ollama上吗?
1
#29 opened 3 months ago
by
huyueeer
Pooling method: mean vs last?
2
#25 opened 3 months ago
by
alexzhou689
Retrieval 效果一般,仅和bm25持平
8
#26 opened 3 months ago
by
Stefan8
Recommanded hyperparameters?
1
#27 opened 3 months ago
by
zhilinw6
请问flash-attn可以关闭吗?是否可以直接使用transformers库里提供的qwen2模型加载?
1
#28 opened 3 months ago
by
shizue
Padding token for batched embedding in Transformers?
1
#24 opened 3 months ago
by
ChrisCrass
Is this model finetuned with MsMarco or mMarco
2
#2 opened 3 months ago
by
rnyak
unable to load the model
1
#1 opened 3 months ago
by
Ratar37003
Do you plan to open-source the training code?
2
#1 opened 3 months ago
by
adol01
What languages are supported?
1
#20 opened 4 months ago
by
jasonrayles
Parameters for peak performance
1
#21 opened 4 months ago
by
cvdbdo
输出的向量维度可以压缩吗?
1
#16 opened 4 months ago
by
sen63
score mteb french
3
#2 opened 4 months ago
by
abhamadi