placeholder tokens are zero initialized
#89 opened about 18 hours ago
by
xdseunghyun
Support for longrope implementation in llama.cpp
1
#88 opened 2 days ago
by
ManniX-ITA
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65fb32f58a66679f92b73458/ozQW6W27tVCM-SRouzGJa.jpeg)
When input tokens < 4096 but total input+output tokens >4096 the model produces poor output
#85 opened 3 days ago
by
einsteiner1983
I'm running out of memory while generating on a RTX A5000 (24 GB)
4
#83 opened 8 days ago
by
xsanskarx
sample code throws TypeError: can only concatenate str (not "dict") to str
#82 opened 10 days ago
by
alxmke
"TypeError: Phi3 is not supported yet." while doing awq quantization using autoAWQ
#81 opened 10 days ago
by
rabinghimire737
![](https://cdn-avatars.huggingface.co/v1/production/uploads/654388272cfe8660a3a2868f/r0144SEPAhJjoyfc4fWZh.jpeg)
Train a BitNet version of Phi 3 Mini?
#80 opened 11 days ago
by
BoscoTheDog
Not implemented the non-interpolated starting token?
#79 opened 19 days ago
by
ryan-minato
![](https://cdn-avatars.huggingface.co/v1/production/uploads/666797f90ec7ed4422ce5c79/Vi9ndXpbyNp4jrzqLBBIu.jpeg)
raise FileMetadataError("Distant resource does not have a Content-Length.") huggingface_hub.utils._errors.FileMetadataError: Distant resource does not have a Content-Length.
3
#77 opened 21 days ago
by
ffeaef
Update the tokenizer which inserted added_tokens to vocab
#75 opened 23 days ago
by
tuong-nguyen-prd
model.generate() is crashing
#74 opened 24 days ago
by
aravindpai
I am trying to use this for some coding tasks (in particular for Java language) and I am getting borderline nonsensical results. Has someone else faced this issue?
2
#72 opened 28 days ago
by
anshumankmr
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65b9f159c29f995b6deeaaf9/8vI8bNXWI1aqTYlNcYWlC.jpeg)
NER using phi3
1
#66 opened about 2 months ago
by
ChiragMa