Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
NVIDIA-Nemotron-3_vllm
Commits
7eff19c5
Commit
7eff19c5
authored
Mar 21, 2026
by
raojy
💬
Browse files
Update model.properties
parent
964ae26c
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
4 deletions
+5
-4
model.properties
model.properties
+5
-4
No files found.
model.properties
View file @
7eff19c5
# 模型唯一标识
modelCode
=
2
095
modelCode
=
2
203
# 模型名称
modelName
=
qwen3.5
_vllm
modelName
=
NVIDIA-Nemotron-3-Super-120B-A12B-BF16
_vllm
# 模型描述
modelDescription
=
Qwen3.5 相对于 Qwen3 系列模型,其 Post-training 性能提升主要来自于对各类 RL 任务和环境的全面扩展,更加强调 RL 环境的难度与可泛化性,而非针对特定指标或狭隘类别的 query 进行优化。
modelDescription
=
Nemotron-3-Super-120B-A12B-BF16 是由英伟达 (NVIDIA) 训练的大语言模型 (LLM),旨在提供强大的智能体 (Agentic)、推理及对话能力。该模型针对协作智能体和高负载工作场景(如 IT 工单自动化)进行了深度优化。与该系列的其他模型类似,它在响应用户查询或任务时,会采取“先生成推理轨迹 (Reasoning Trace),后给出最终回复”的模式。此外,模型的推理能力可以通过聊天模板中的标志位 (Flag) 进行灵活配置。
# 运行过程
processType
=
推理
# 算法类别
...
...
@@ -11,4 +12,4 @@ appCategory=对话问答
# 框架类型
frameType
=
vllm
# 加速卡类型
accelerateType
=
K100AI,
BW1000
accelerateType
=
BW1000
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment