[Model] Consolidate Deepseek-MoE implementation with DeepSeek-v2 (#28101)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Isotr0py
2025-11-08 05:01:27 +00:00
committed by GitHub
co-authored by Kunshang Ji
parent 70af44fd10
commit 934a9c3b79
6 changed files with 144 additions and 548 deletions
+4 -1
View File
@@ -219,7 +219,10 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
"nvidia/Llama-3_3-Nemotron-Super-49B-v1",
trust_remote_code=True,
),
"DeepseekForCausalLM": _HfExamplesInfo("deepseek-ai/deepseek-llm-7b-chat"),
"DeepseekForCausalLM": _HfExamplesInfo(
"deepseek-ai/deepseek-moe-16b-base",
trust_remote_code=True,
),
"DeepseekV2ForCausalLM": _HfExamplesInfo(
"deepseek-ai/DeepSeek-V2-Lite-Chat",
trust_remote_code=True,