 Georgi Gerganov
|
77a73403ca
ggml : add new Q4_2 quantization (ARM only) (#1046)
|
il y a 2 ans |
 Stephan Walter
|
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709)
|
il y a 2 ans |
 Slaren
|
64bde3ffd4
Fix ggml_init_params in quantize
|
il y a 2 ans |
|
Stephan Walter
|
436e561931
all : be more strict about converting float to double (#458)
|
il y a 2 ans |
|
Stephan Walter
|
c1f885067c
ggml : introduce structs for the q4 data blocks (#356)
|
il y a 2 ans |
|
Georgi Gerganov
|
a316a425d0
Overhaul the examples structure
|
il y a 2 ans |
