Resources

View closed (14)

Messages about new models and report

pinned

#27 opened 3 months ago by

infgrad

Update modeling.py

#32 opened 21 days ago by

sigridjineth

需要比对的文本比较大，往往超过5000字中文，有什么好办法。试了拆分向量化再组合，效果不好。

#29 opened 2 months ago by

springsuu

Ragged Batching Support

#26 opened 3 months ago by

jholm117

Fix CPU Fallback for NewAttention with xformers BlockDiagonalMask

#25 opened 3 months ago by

m7mdhka

Risks of Remote Code Execution.

#22 opened 4 months ago by

MeanBean-05

Error in running the model in CPU

#17 opened 5 months ago by

Navanit-AI

Best Practice for fine-tuning

#16 opened 5 months ago by

Ehsanl

Training Details

#15 opened 5 months ago by

sh1tp0st3r

Embedding documents with this model

#14 opened 5 months ago by

dayosalam

Generate ONNX

#12 opened 6 months ago by

masdeval

Getting Error : No operator found for `memory_efficient_attention_forward`

#11 opened 7 months ago by

iabhishekofficial

About Quantized Models

#8 opened 7 months ago by

infgrad

GGUF

#7 opened 7 months ago by

aliiakaay

Discrepancies in Model Output Precision and Warning Messages

#6 opened 7 months ago by

razsoriginals

Quantized versions

#5 opened 7 months ago by

tDudu78

Add Transformers.js usage code

#4 opened 8 months ago by

Xenova

Upload ONNX weights

#3 opened 8 months ago by