Issues
- 6
- 1
- 0
Need some information about the tokenizer
#29 opened by xtfocus - 1
- 3
Evaluation lack of context
#25 opened by vTuanpham - 8
Error message: "llama.cpp error: 'done_getting_tensors: wrong number of tensors; expected 388, got 195'"
#23 opened by jackNhat - 1
hardware requirements to run finetune
#26 opened by trung-nw - 1
4/8-bit with bitsandbytes
#19 opened by datquocnguyen - 5
- 1
Do you have any plan for building a bi-lingual language English - Vietnames in the future?
#21 opened by leviethung2103 - 3
- 7
(Google Colab) ImportError: cannot import name '_expand_mask' from 'transformers.models.bloom.modeling_bloom'
#3 opened by phatjkk - 10
- 1
Redistributing the model in other format
#18 opened by nviet - 4
- 1
- 1
[Question] Hardware requirements with vLLM
#13 opened by hodacthanhminh - 1
Context Window of PhoGPT ?
#14 opened by xnohat - 2
How can I get the model to run on vLLM?
#12 opened by xnoname79 - 1
Could you explain what is the diference the non-instruct and instruct PhoGPT verrsion ?
#9 opened by leviethung2103 - 1
- 3
- 1
Any online demo available?
#8 opened by anguyen8 - 6
- 1
- 1
Hardware specification for inference
#2 opened by leviethung2103 - 3
License problem
#1 opened by eleluong