NouamaneTazi / bloomz.cpp

C++ implementation for BLOOM

NouamaneTazi/bloomz.cpp Issues

download and convert the 7B1 model to ggml FP16 format fails!
Updated 4 months ago
May you release a windows build binary?
Updated 6 months ago4
Convert bloomz-7b1-mt to ggml error.
Updated 8 months ago
Convert HF to ggml error.
Updated 9 months ago
-n param doesn't work?
Updated 9 months ago
Quantization doesn't work with Bloomz 176B
Updated 9 months ago10
Running 'make' warnings in bloom_model_load() function
Closed 10 months ago1
Bloomz 176B inference doesn't work
Updated 10 months ago9
Something wrong with the tokenize function.
Updated a year ago
Eval result is wrong compare to huggingface
Closed a year ago
several questions
Updated a year ago1
error
Updated a year ago
document sampling parameters and/or minimal "viable" codegen model ?
Updated a year ago1
Is there any plan for mT0 model support?
Updated a year ago1
There was a problem loading the model
Updated a year ago1
setting -t 8 (n_threads) "locks" the python process
Updated a year ago
[Open-to-community] Benchmark bloomz.cpp on different hardware
Updated a year ago6
Load a ggml model from the hub
Updated a year ago
[RFE] Add interactive mode
Updated a year ago3
Quantised model?
Closed a year ago2