Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
ModelZoo
NVIDIA-Nemotron-3
Commits
e2f8c8df
Commit
e2f8c8df
authored
May 28, 2026
by
weishb
Browse files
修改模板
parent
c24e56ea
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
12 additions
and
9 deletions
+12
-9
README.md
README.md
+11
-8
model.properties
model.properties
+1
-1
No files found.
README.md
View file @
e2f8c8df
...
...
@@ -47,10 +47,18 @@ docker run -it --shm-size 200g \
```
pip uninstall vllm
pip uninstall numpy
pip install vllm-0.15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
pip install vllm-0.15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
--no-deps
pip install numpy==1.26.1
```
## 预训练权重
**请根据`支持的DCU型号`选择对应模型下载,FP8模型仅在BW1100/BW1101上支持,其他型号请勿使用!**
|
**模型名称**
|
**权重大小**
|
**DCU型号**
|
**最低卡数需求**
|
**下载地址**
|
| :-----------------------------: | :----------: | :-----------: | :--------------: | :----------------------------------------------------------: |
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | 120B | BW1000 | 8 |
[
Hugging Face
](
https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
)
|
## 数据集
暂无
...
...
@@ -61,7 +69,7 @@ pip install numpy==1.26.1
## 推理
### v
llm
### v
LLM
#### 单机推理
...
...
@@ -108,15 +116,10 @@ curl http://localhost:8000/v1/chat/completions \
DCU 与 GPU 精度一致,推理框架:vllm。
## 预训练权重
|
**模型名称**
|
**权重大小**
|
**DCU型号**
|
**最低卡数需求**
|
**下载地址**
|
| :-----------------------------: | :----------: | :-----------: | :--------------: | :----------------------------------------------------------: |
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | 120B | BW1000 | 8 |
[
Hugging Face
](
https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
)
|
## 源码仓库及问题反馈
-
[
https://developer.sourcefind.cn/codes/modelzoo/nvidia-nemotron-3_vllm
](
https://developer.sourcefind.cn/codes/modelzoo/nvidia-nemotron-3
_vllm
)
-
[
https://developer.sourcefind.cn/codes/modelzoo/nvidia-nemotron-3_vllm
](
https://developer.sourcefind.cn/codes/modelzoo/nvidia-nemotron-3
)
## 参考资料
...
...
model.properties
View file @
e2f8c8df
# 模型唯一标识
modelCode
=
2203
# 模型名称
modelName
=
NVIDIA-Nemotron-3
_vllm
modelName
=
NVIDIA-Nemotron-3
# 模型描述
modelDescription
=
Nemotron-3 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
...
...
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