Phi-3-small-128k-instruct-onnx-cuda
#40 opened 3 days ago
by
Andreas999
Upgrade to a newer transformers version
#39 opened 30 days ago
by
the-mysh
Phi-3-small-128k-instruct-coding-ensemble-mcettrick
#38 opened 4 months ago
by
mcettrick-ai
add AIBOM
#36 opened 6 months ago
by
sabato-nocera
Improve model card: Add library name
#35 opened 9 months ago
by
nielsr
Error in Flash Attention
#34 opened about 1 year ago
by
Sayan01
Resolve - 196 [rank0]: triton.runtime.autotuner.OutOfResources: out of resource: shared memory, Required: 180224, Hardware limit: 101376. Reducing block sizes or `num_stages` may help.
1
#33 opened about 1 year ago
by
moidhassan
Issue with Rope Scaling
1
#31 opened over 1 year ago
by
ritwickchaudhryamazon
AssertionError: Flash Attention is not available, but is needed for dense attention
3
#30 opened over 1 year ago
by
tpadhi1
Fast Tokenization for Phi3-small
#29 opened over 1 year ago
by
mfajcik
update positional_embedding.py
#28 opened over 1 year ago
by
mwirth-epo
"OutOfResources: out of resource: shared memory, Required: 180224, Hardware limit: 101376. "
1
#27 opened over 1 year ago
by
joker26
Slower generation with multi-batch size.
#26 opened over 1 year ago
by
Satandon1999
why only small model use MuP ?
#24 opened over 1 year ago
by
xdseunghyun
tokenizer gives unexpected results
#23 opened over 1 year ago
by
jpiabrantes
Does it support system?
#22 opened over 1 year ago
by
lucasjin
Upload triton_flash_blocksparse_attn.py
#21 opened over 1 year ago
by
barcelosallan
"TypeError: phi3 isn't supported yet ". Could not quantize the phi3 model using the AWQ quantization method.
3
#20 opened over 1 year ago
by
rabinghimire737
Multi-GPU case device mismatch while finetuning.
➕
1
3
#19 opened over 1 year ago
by
Satandon1999
CheckpointError in `triton_flash_blocksparse_attn.py` while finetuning
1
#18 opened over 1 year ago
by
FremyCompany
Fix for FlashAttention RuntimeError & Triton Multi GPU fix.
1
#17 opened over 1 year ago
by
Satandon1999
Out of resource: shared memory
6
#16 opened over 1 year ago
by
iszhaoxin
RuntimeError: FlashAttention only support fp16 and bf16 data type
1
#15 opened over 1 year ago
by
Satandon1999
Adding sample_finetune.py to small model
👍
1
1
#9 opened over 1 year ago
by
hackint0sh
The attention mask and the pad token id were not set
#8 opened over 1 year ago
by
hamidpalangi