diff --git a/docs/android.md b/doc/android.md
similarity index 100%
rename from docs/android.md
rename to doc/android.md
diff --git a/docs/backend/BLIS.md b/doc/backend/BLIS.md
similarity index 100%
rename from docs/backend/BLIS.md
rename to doc/backend/BLIS.md
diff --git a/docs/backend/CANN.md b/doc/backend/CANN.md
similarity index 99%
rename from docs/backend/CANN.md
rename to doc/backend/CANN.md
index 23f10175a6b2d..de84c9e465ff8 100644
--- a/docs/backend/CANN.md
+++ b/doc/backend/CANN.md
@@ -15,7 +15,7 @@
 
 **Ascend NPU** is a range of AI processors using Neural Processing Unit. It will efficiently handle matrix-matrix multiplication, dot-product and scalars.
 
-**CANN** (Compute Architecture for Neural Networks) is a heterogeneous computing architecture for AI scenarios, providing support for multiple AI frameworks on the top and serving AI processors and programming at the bottom. It plays a crucial role in bridging the gap between upper and lower layers, and is a key platform for improving the computing efficiency of Ascend AI processors. Meanwhile, it offers a highly efficient and easy-to-use programming interface for diverse application scenarios, allowing users to rapidly build AI applications and services based on the Ascend platform.
+**CANN** (Compute Architecture for Neural Networks) is a heterogeneous computing architecture for AI scenarios, providing support for multiple AI frameworks on the top and serving AI processors and programming at the bottom. It plays a crucial role in bridging the gap between upper and lower layers, and is a key platform for improving the computing efficiency of Ascend AI processors. Meanwhile, it offers a highly efficient and easy-to-use programming interface for diverse application scenarios, allowing users to rapidly build AI applications and services based on the Alsscend platform.
 
 **Llama.cpp + CANN**
 
diff --git a/docs/backend/SYCL.md b/doc/backend/SYCL.md
similarity index 100%
rename from docs/backend/SYCL.md
rename to doc/backend/SYCL.md
diff --git a/docs/build.md b/doc/build.md
similarity index 100%
rename from docs/build.md
rename to doc/build.md
diff --git a/docs/development/HOWTO-add-model.md b/doc/development/HOWTO-add-model.md
similarity index 100%
rename from docs/development/HOWTO-add-model.md
rename to doc/development/HOWTO-add-model.md
diff --git a/docs/development/debugging-tests.md b/doc/development/debugging-tests.md
similarity index 100%
rename from docs/development/debugging-tests.md
rename to doc/development/debugging-tests.md
diff --git a/docs/development/llama-star/idea-arch.key b/doc/development/llama-star/idea-arch.key
similarity index 100%
rename from docs/development/llama-star/idea-arch.key
rename to doc/development/llama-star/idea-arch.key
diff --git a/docs/development/llama-star/idea-arch.pdf b/doc/development/llama-star/idea-arch.pdf
similarity index 100%
rename from docs/development/llama-star/idea-arch.pdf
rename to doc/development/llama-star/idea-arch.pdf
diff --git a/docs/development/token_generation_performance_tips.md b/doc/development/token_generation_performance_tips.md
similarity index 100%
rename from docs/development/token_generation_performance_tips.md
rename to doc/development/token_generation_performance_tips.md
diff --git a/docs/docker.md b/doc/docker.md
similarity index 100%
rename from docs/docker.md
rename to doc/docker.md
diff --git a/docs/install.md b/doc/install.md
similarity index 100%
rename from docs/install.md
rename to doc/install.md
diff --git a/doc/issue.md b/doc/issue.md
new file mode 100644
index 0000000000000..f500be25a2dd4
--- /dev/null
+++ b/doc/issue.md
@@ -0,0 +1,4 @@
+# git
+
+if you modify doc/build.md, you cannot git add it, because it is in .gitignore file
+
diff --git a/doc/story.md b/doc/story.md
new file mode 100644
index 0000000000000..1578fba6433e4
--- /dev/null
+++ b/doc/story.md
@@ -0,0 +1,47 @@
+# Complie
+
+doc/build.md
+
+# model
+
+[prithivMLmods/Llama-Deepsync-1B-GGUF](https://huggingface.co/prithivMLmods/Llama-Deepsync-1B-GGUF)
+
+# Run model
+
+./build/bin/llama-cli -m models/Llama-Deepsync-1B.Q4_K_M.gguf -p "what's your name"
+
+# Specific parameter
+
+cd /home/xunchan/Workspace/llama.xunchan/gguf-py/examples
+
+python reader.py  /home/xunchan/Workspace/llama.xunchan/models/Llama-Deepsync-1B.Q4_K_M.gguf
+
+or
+
+show in [huggingface](https://huggingface.co/) frontend
+
+## general.architecture
+
+llama
+
+## llama
+
+### llama.block_count
+
+### llama.context_length
+
+### llama.embedding_length
+
+### llama.feed_forward_length
+
+### 
+
+#### block
+
+# Modify code
+
+## Find the llama block code process location
+
+## Write it precifily
+
+## 
\ No newline at end of file