423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-28 19:24:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] ktransformers qwen3 support (#9485)

Browse Source 
Co-authored-by: unknown <xiongchenhui@hisense.ad>
This commit is contained in:
Pory 2025-11-13 20:09:44 +08:00 committed by GitHub
parent 0aa4a051af
commit 10a446e373
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/model/model_utils/ktransformers.py
View File

@ -34,6 +34,7 @@ if KT_AVAILABLE:
from ktransformers.models.modeling_llama import LlamaForCausalLM
from ktransformers.models.modeling_mixtral import MixtralForCausalLM
from ktransformers.models.modeling_qwen2_moe import Qwen2MoeForCausalLM
from ktransformers.models.modeling_qwen3_moe import Qwen3MoeForCausalLM
from ktransformers.optimize.optimize import optimize_and_load_gguf
from ktransformers.server.config.config import Config
from ktransformers.sft.lora import inject_lora_layer
@ -71,6 +72,7 @@ def load_kt_pretrained_model(config: "PretrainedConfig", model_args: "ModelArgum
"DeepseekV2ForCausalLM": DeepseekV2ForCausalLM,
"DeepseekV3ForCausalLM": DeepseekV3ForCausalLM,
"Qwen2MoeForCausalLM": Qwen2MoeForCausalLM,
"Qwen3MoeForCausalLM": Qwen3MoeForCausalLM,
"LlamaForCausalLM": LlamaForCausalLM,
"MixtralForCausalLM": MixtralForCausalLM,
}