mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-16 11:36:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : support converting Mistral Small text-only (#12450)

Browse Source
This commit is contained in:
Xuan-Son Nguyen 2025-03-18 19:16:19 +01:00 committed by GitHub
parent c6af2161b2
commit 29fff308c7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
convert_hf_to_gguf.py
View File

@ -1747,6 +1747,25 @@ class LlamaModel(Model):
raise ValueError(f"Unprocessed experts: {experts}") raise ValueError(f"Unprocessed experts: {experts}")
@Model.register("Mistral3ForConditionalGeneration")
class Mistral3Model(LlamaModel):
model_arch = gguf.MODEL_ARCH.LLAMA
# we need to merge the text_config into the root level of hparams
def __init__(self, *args, **kwargs):
hparams = Model.load_hparams(kwargs["dir_model"])
if "text_config" in hparams:
hparams = {**hparams, **hparams["text_config"]}
kwargs["hparams"] = hparams
super().__init__(*args, **kwargs)
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None):
name = name.replace("language_model.", "")
if "multi_modal_projector" in name or "vision_tower" in name:
return []
return super().modify_tensors(data_torch, name, bid)
@Model.register("DeciLMForCausalLM") @Model.register("DeciLMForCausalLM")
class DeciModel(Model): class DeciModel(Model):
model_arch = gguf.MODEL_ARCH.DECI model_arch = gguf.MODEL_ARCH.DECI