Issues
- 1
Is it possible to make multiple socket connection at the same time from same machine.
#44 opened by ZTAP0011 - 2
Segfault on large inputs?
#37 opened by corani - 1
How can I increase n_max_tokens?
#43 opened by ztkg257 - 1
How do I properly build this on windows?
#42 opened by qwbarch - 0
Any plan to support GGUF?
#41 opened by Jeevhi - 6
Is this ever going to be updated?
#39 opened by BBC-Esq - 1
Does this support CUDA?
#40 opened by SpaceCowboy850 - 3
- 4
Issue reading ggml-model-q4_0.bin
#38 opened by thijse - 11
- 1
Error Running Server Example
#28 opened by BradSmith2015 - 18
Classification Pipeline
#11 opened by okpatil4u - 6
subword `#` should be an option.
#33 opened by FFengIll - 1
- 4
converter does not work with the current ggml
#23 opened by yunghoy - 0
Error load model
#34 opened by AgostinoA - 0
Comparison of timing results
#30 opened by mgoldenbe - 0
throwing the error while running the model
#27 opened by Jasheenshaik - 3
- 2
update to current ggml
#24 opened by manwantnosmoke - 9
- 0
- 4
About the calculation of overhead.
#19 opened by znsoftm - 5
Unable to build static library
#17 opened by jjzazuet - 2
why does the program ignore the three layers?
#18 opened by znsoftm - 0
I really appreciate your kind words about our project! May I ask which model and configuration of CPU you are using?
#16 opened by zhengbohennuli - 3
CodeBERT
#7 opened by walking-octopus - 1
Cannot build " set_target_properties Can not find target to add properties to: ggml"
#14 opened by chrisbward - 1
Running `bert_load_from_file` from code results with ` 'embeddings.word_embeddings.weight' has wrong shape in model file`
#13 opened by NitayRabi - 1
BrokenPipeError: [Errno 32] Broken pipe
#8 opened by virajk31 - 1
convert 'chatglm-6b' model failed
#5 opened by lindeer - 1
- 0
Provide C api in bert.h
#2 opened by skeskinen - 1
Q&A example?
#3 opened by walking-octopus