model: support Ministral3 (#17644)

* conversion script

* support ministral 3

* maybe this is better?

* add TODO for rope_yarn_log_mul

* better ppl (tested on 14B-Instruct)

* Add Ministral3 support to Mistral format

* improve arch handling

* add sizes

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* nits

---------

Co-authored-by: Julien Denize <julien.denize@mistral.ai>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Xuan-Son Nguyen
2025-12-01 12:26:52 +01:00
committed by GitHub
co-authored by Sigbjørn Skjæret Julien Denize
parent 649495c9d9
commit cd3c118908
11 changed files with 342 additions and 10 deletions
+3
View File
@@ -904,6 +904,9 @@ class GGUFWriter:
def add_attn_temperature_length(self, value: int) -> None:
self.add_uint32(Keys.Attention.TEMPERATURE_LENGTH.format(arch=self.arch), value)
def add_attn_temperature_scale(self, value: float) -> None:
self.add_float32(Keys.Attention.TEMPERATURE_SCALE.format(arch=self.arch), value)
def add_pooling_type(self, value: PoolingType) -> None:
self.add_uint32(Keys.LLM.POOLING_TYPE.format(arch=self.arch), value.value)