Skip to content

Commit ee074de

Browse files
committed
fix doc
1 parent c7a209c commit ee074de

2 files changed

Lines changed: 7 additions & 7 deletions

File tree

‎README.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -181,7 +181,7 @@ This section lists converted GGUF models that can be used directly with `model-s
181181
<tr>
182182
<td rowspan="3">SmolVLA</td>
183183
<td rowspan="3">SO-101</td>
184-
<td rowspan="3"><code>smolvla_450m_grasp_50k</code> (local checkpoint)</td>
184+
<td rowspan="3">-</td>
185185
<td>bf16</td>
186186
<td><a href="https://huggingface.co/rrobottt/smolvla-so101-bf16">smolvla-so101-bf16</a></td>
187187
</tr>
@@ -202,11 +202,11 @@ This section lists converted GGUF models that can be used directly with `model-s
202202
</tr>
203203
<tr>
204204
<td>f16</td>
205-
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-fp16">smolvla-libero-fp16</a></td>
205+
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-f16">smolvla-libero-f16</a></td>
206206
</tr>
207207
<tr>
208208
<td>f32</td>
209-
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-fp32">smolvla-libero-fp32</a></td>
209+
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-f32">smolvla-libero-f32</a></td>
210210
</tr>
211211
<tr>
212212
<td rowspan="3">pi0</td>

‎README_ZH.md‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -165,7 +165,7 @@ bash robot_client/shell/cpp_client_example.sh
165165

166166
## 🧩 model-zoo
167167

168-
这里整理一些已经转换好的 GGUF 模型,可以直接配合 `model-server` 做smoke test,以方便quick start!但针对自己的实际场景,我们推荐使用[hf2gguf](tools/hf2gguf/README_ZH.md)l来生成自己的GGUF model!并且对于不同的部分,您还可以自定义不同的精度,来实现不同部分的精度组合(事实上,不同部分的最优精度通常是不同的),我们的例子中,state proj始终保持f32精度,其他的gguf随着precision精度变化而变化,您可以自行组合,探索更好更高效的性能tradeoff!
168+
这里整理一些已经转换好的 GGUF 模型,可以直接配合 `model-server` 做smoke test,以方便quick start!但针对自己的实际场景,我们推荐使用[hf2gguf](tools/hf2gguf/README_ZH.md)来生成自己的GGUF model!并且对于不同的部分,您还可以自定义不同的精度,来实现不同部分的精度组合(事实上,不同部分的最优精度通常是不同的),我们的例子中,state proj始终保持f32精度,其他的gguf随着precision精度变化而变化,您可以自行组合,探索更好更高效的性能tradeoff!
169169

170170
<table>
171171
<thead>
@@ -181,7 +181,7 @@ bash robot_client/shell/cpp_client_example.sh
181181
<tr>
182182
<td rowspan="3">SmolVLA</td>
183183
<td rowspan="3">SO-101</td>
184-
<td rowspan="3"><code>smolvla_450m_grasp_50k</code>(本地 checkpoint)</td>
184+
<td rowspan="3">-</td>
185185
<td>bf16</td>
186186
<td><a href="https://huggingface.co/rrobottt/smolvla-so101-bf16">smolvla-so101-bf16</a></td>
187187
</tr>
@@ -202,11 +202,11 @@ bash robot_client/shell/cpp_client_example.sh
202202
</tr>
203203
<tr>
204204
<td>f16</td>
205-
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-fp16">smolvla-libero-fp16</a></td>
205+
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-f16">smolvla-libero-f16</a></td>
206206
</tr>
207207
<tr>
208208
<td>f32</td>
209-
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-fp32">smolvla-libero-fp32</a></td>
209+
<td><a href="https://huggingface.co/rrobottt/smolvla-libero-f32">smolvla-libero-f32</a></td>
210210
</tr>
211211
<tr>
212212
<td rowspan="3">pi0</td>

0 commit comments

Comments
 (0)