thomasantony / llamacpp-python

Python bindings for llama.cpp

thomasantony/llamacpp-python Issues

KeyError: 'transformer.h.0.attn.c_attn.bias'
Closed 3 months ago
Update llamacpp
Updated 10 months ago
Not work
Updated a year ago1
batch inference?
Updated a year ago
Update for llama.cpp quantization changes
Updated a year ago
Better support for editable install
Closed a year ago3
delete
Closed a year ago
unable to convert
Updated a year ago
Are you even tested with code?
Closed a year ago2
Clean up llamacpp-chat interface
Updated a year ago1
how to set customized tokenizer?
Updated a year ago
Updating to latest llama.cpp version
Closed a year ago1
AttributeError: module 'llamacpp' has no attribute 'llama_model_quantize'
Closed a year ago2
ImportError: DLL load failed while importing _pyllamacpp: A DLL initialization routine failed.
Closed a year ago1
Llama Inference not working
Closed a year ago3
Segmentation fault for generations larger than ~512 tokens
Updated a year ago4
Better command-line argument parsing for cli.py and chat.py
Updated a year ago
It it possible to reset the model context for use as a REST API?
Closed a year ago1
problem with llama-convert
Closed a year ago4
Adding new params
Closed a year ago3
Script crash with no output
Updated a year ago1