 Piotr Wilkin
|
5417f3294b
Wrong dimension order
|
il y a 3 mois |
|
Piotr Wilkin
|
4d571eda07
Let's dump extra tensors
|
il y a 3 mois |
|
Piotr Wilkin
|
554593d60d
Variable scopes are fun
|
il y a 3 mois |
|
Piotr Wilkin
|
0b301889bf
Stabilize tensor dump trigger for now with -n < 50
|
il y a 3 mois |
|
Piotr Wilkin
|
f0a07c1091
Add proper backend tensor printing, use double for accumulating the sum
|
il y a 3 mois |
|
Piotr Wilkin
|
5306640300
All's well that ends in a well
|
il y a 3 mois |
|
Piotr Wilkin
|
22ee5a971b
Add gate_sigmoid to callback
|
il y a 3 mois |
 Joshua Cogliati
|
d35a1e8c41
cli : change log to warning to explain reason for stopping (#15604)
|
il y a 4 mois |
 Diego Devesa
|
f75b830647
chat : include kwargs in template example (#15309)
|
il y a 5 mois |
 Molly Sophia
|
c82d48ec23
llama : fix `--reverse-prompt` crashing issue (#14794)
|
il y a 6 mois |
 Sigbjørn Skjæret
|
abf241045d
main : honor --verbose-prompt on interactive prompts (#14350)
|
il y a 6 mois |
|
Molly Sophia
|
72c6bc3f3d
llama : better rwkv chat template and add missing `inputs.use_jinja` setting (#14336)
|
il y a 6 mois |
 Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
il y a 7 mois |
|
Diego Devesa
|
27ebfcacba
llama : do not crash if there is no CPU backend (#13395)
|
il y a 8 mois |
|
Georgi Gerganov
|
51fb96b1ff
context : remove logits_all flag (#13284)
|
il y a 8 mois |
|
Diego Devesa
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
il y a 8 mois |
