| .. |
|
embedding
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 лет назад |
|
main
|
2663d2c678
Windows fixes (#890)
|
2 лет назад |
|
perplexity
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 лет назад |
|
quantize
|
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)
|
2 лет назад |
|
quantize-stats
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 лет назад |
|
CMakeLists.txt
|
62cfc54f77
Add quantize-stats command for testing quantization (#728)
|
2 лет назад |
|
Miku.sh
|
ff05d05c96
miku.sh : add executable bit (#780)
|
2 лет назад |
|
alpaca.sh
|
55ad42af84
Move chat scripts into "./examples"
|
2 лет назад |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
2 лет назад |
|
chat-13B.sh
|
55ad42af84
Move chat scripts into "./examples"
|
2 лет назад |
|
chat.sh
|
79b2b266db
If n_predict == -1, generate forever
|
2 лет назад |
|
common.cpp
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 лет назад |
|
common.h
|
f963b63afa
Rewrite loading code to try to satisfy everyone:
|
2 лет назад |
|
gpt4all.sh
|
6e7801d08d
examples : add gpt4all script (#658)
|
2 лет назад |
|
reason-act.sh
|
a6956b25a1
add example of re-act pattern (#583)
|
2 лет назад |
Stephan Walter
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)