docs(research): 更新调研报告至v2.0反映NVIDIA选型
- 调研报告从RouteLLM BERT切换为NVIDIA多头分类器作为推荐方案 - 新增选型变更记录、复杂度评分公式、测试结果 - 更新tx402技术对比表和演进路线 - nvidia_router.py添加use_safetensors=True兼容transformers 4.57
This commit is contained in:
@@ -43,7 +43,8 @@ class NvidiaMultiHeadClassifier(nn.Module):
|
||||
# DeBERTa backbone
|
||||
self.backbone = DebertaV2Model.from_pretrained(
|
||||
config.base_model,
|
||||
ignore_mismatched_sizes=True
|
||||
ignore_mismatched_sizes=True,
|
||||
use_safetensors=True
|
||||
)
|
||||
|
||||
hidden_size = 768 # DeBERTa-v3-base
|
||||
|
||||
Reference in New Issue
Block a user