llama.cpp
Feat: Support for `falcon-mamba` architecture
#9074
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
18
Changes
View On
GitHub
Commits
feat: initial support for llama.cpp
younesbelkada
committed
2 years ago
fix: lint
younesbelkada
committed
2 years ago
refactor: better refactor
younesbelkada
committed
2 years ago
Update src/llama.cpp
younesbelkada
committed
2 years ago
Update src/llama.cpp
younesbelkada
committed
2 years ago
fix: address comments
younesbelkada
committed
2 years ago
Update convert_hf_to_gguf.py
younesbelkada
committed
2 years ago
fix: add more cleanup and harmonization
younesbelkada
committed
2 years ago
fix: lint
younesbelkada
committed
2 years ago
Update gguf-py/gguf/gguf_writer.py
younesbelkada
committed
2 years ago
fix: change name
younesbelkada
committed
2 years ago
Apply suggestions from code review
younesbelkada
committed
2 years ago
add in operator
younesbelkada
committed
2 years ago
fix: add `dt_b_c_rms` in `llm_load_print_meta`
younesbelkada
committed
2 years ago
fix: correct printf format for bool
younesbelkada
committed
2 years ago
fix: correct print format
younesbelkada
committed
2 years ago
Update src/llama.cpp
younesbelkada
committed
2 years ago
llama : quantize more Mamba tensors
compilade
committed
2 years ago
Loading