Update README.md

README.md

@@ -37,3 +37,146 @@ For those who are interested in model conversion, you can try to export axmodel
 |Chips|w8a16|w4a16|
 |--|--|--|
 |AX650| 2.7 tokens/sec|5 tokens/sec|
+
+
+## How to use
+
+Download all files from this repository to the device
+
+```
+root@ax650:/mnt/qtang/llm-test/deepseek-r1-7b# tree -L 1
+.
+├── deepseek-r1-7b-gptq-int4-ax650
+├── deepseek-r1_tokenizer
+├── deepseek-r1_tokenizer.py
+├── main_axcl_aarch64
+├── main_axcl_x86
+├── main_prefill
+├── post_config.json
+├── run_deepseek-r1_7b_gptq_int4_ax650.sh
+├── run_deepseek-r1_7b_gptq_int4_axcl_aarch64.sh
+└── run_deepseek-r1_7b_gptq_int4_axcl_x86.sh
+```
+
+#### Start the Tokenizer service
+
+```
+root@ax650:/mnt/qtang/llm-test/deepseek-r1-7b# python deepseek-r1_tokenizer.py --port 12345
+151646 <｜begin▁of▁sentence｜> 151643 <｜end▁of▁sentence｜>
+<｜begin▁of▁sentence｜>You are DeepSeek-R1, You are a helpful assistant.<｜User｜>hello world<｜Assistant｜>
+[151646, 151646, 2610, 525, 18183, 39350, 10911, 16, 11, 1446, 525, 264, 10950, 17847, 13, 151644, 14990, 1879, 151645]
+http://localhost:12345
+```
+
+#### Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) or AX650N DEMO Board
+
+Open another terminal and run `run_deepseek-r1_7b_gptq_int4_ax650.sh`
+
+```
+root@ax650:/mnt/qtang/llm-test/deepseek-r1-7b# ./run_deepseek-r1_7b_gptq_int4_ax650.sh
+[I][                            Init][ 125]: LLM init start
+bos_id: 151646, eos_id: 151643
+  3% | ██                                |   1 /  31 [0.00s<0.09s, 333.33 count/s] tokenizer init ok
+100% | ████████████████████████████████ |  31 /  31 [45.25s<45.25s, 0.69 count/s] init post axmodel ok,remain_cmm(7664 MB)[I][
+[I][                            Init][ 246]: kv_cache_size : 512, kv_cache_num: 1024
+[I][                            Init][ 254]: prefill_token_num : 128
+[I][                     load_config][ 281]: load config:
+{
+    "enable_repetition_penalty": false,
+    "enable_temperature": true,
+    "enable_top_k_sampling": true,
+    "enable_top_p_sampling": false,
+    "penalty_window": 20,
+    "repetition_penalty": 1.2,
+    "temperature": 0.9,
+    "top_k": 10,
+    "top_p": 0.8
+}
+
+[I][                            Init][ 268]: LLM init ok
+Type "q" to exit, Ctrl+c to stop current running
+<think>
+I'm DeepSeek-R1, an AI assistant created exclusively by the Chinese Company DeepSeek.
+I specialize in helping you tackle complex mathematical, coding, and logical challenges. I'll do my best to assist you.
+</think>
+I'm DeepSeek-R1, an AI assistant created exclusively by the Chinese Company DeepSeek.
+ I specialize in helping you tackle complex mathematical, coding, and logical challenges. I'll do my best to assist you.
+[N][                             Run][ 605]: hit eos,avg 4.52 token/s
+```
+
+#### Inference with M.2 Accelerator card
+
+[What is M.2 Accelerator card?](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html), Show this DEMO based on Raspberry PI 5.
+
+Open another terminal and run `run_deepseek-r1_7b_gptq_int4_axcl_aarch64.sh`
+
+```
+(base) axera@raspberrypi:~/samples/deepseek-r1-7b-gptq-int4 $ ./run_deepseek-r1_7b_gptq_int4_axcl_aarch64.sh
+build time: Feb 13 2025 15:15:07
+[I][                            Init][ 111]: LLM init start
+bos_id: 151646, eos_id: 151643
+100% | ████████████████████████████████ |  31 /  31 [67.43s<67.43s, 0.46 count/s] init post axmodel okremain_cmm(2739 MB)
+[I][                            Init][ 226]: max_token_len : 1024
+[I][                            Init][ 231]: kv_cache_size : 512, kv_cache_num: 1024
+[I][                     load_config][ 282]: load config:
+{
+    "enable_repetition_penalty": false,
+    "enable_temperature": true,
+    "enable_top_k_sampling": true,
+    "enable_top_p_sampling": false,
+    "penalty_window": 20,
+    "repetition_penalty": 1.2,
+    "temperature": 0.9,
+    "top_k": 10,
+    "top_p": 0.8
+}
+
+[I][                            Init][ 288]: LLM init ok
+Type "q" to exit, Ctrl+c to stop current running
+>> 直角三角形两直角边是3和4，斜边是多少？简单思考
+<think>
+首先，我需要找到一个直角三角形的斜边长度。已知两条直角边的长度分别是3和4。
+根据勾股定理，斜边的平方等于两条直角边的平方之和。因此，我可以计算出斜边长度的平方为3的平方加上4的平方，即9加上16，等于25。
+然后，通过对25的平方根运算，我得到斜边的长度是5。
+最终，斜边的长度是5。
+</think>
+
+要找到直角三角形的斜边长度，已知两条直角边的长度分别为3和4。我们可以使用勾股定理来计算斜边长度。
+勾股定理的表达式是：
+\[
+c = \sqrt{a^2 + b^2}
+\]
+其中：
+- \( c \) 是斜边的长度，
+- \( a \) 和 \( b \) 是两条直角边的长度。
+将已知数值代入公式：
+\[
+c = \sqrt{3^2 + 4^2} = \sqrt{9 + 16} = \sqrt{25} = 5
+\]
+因此，斜边的长度是：
+\[
+\boxed{5}
+\]
+[N][                             Run][ 605]: hit eos,avg 4.64 token/s
+>> q
+
+(base) axera@raspberrypi:~ $ axcl-smi
++------------------------------------------------------------------------------------------------+
+| AXCL-SMI  V2.26.0_20250206225448                                Driver  V2.26.0_20250206225448 |
++-----------------------------------------+--------------+---------------------------------------+
+| Card  Name                     Firmware | Bus-Id       |                          Memory-Usage |
+| Fan   Temp                Pwr:Usage/Cap | CPU      NPU |                             CMM-Usage |
+|=========================================+==============+=======================================|
++-----------------------------------------+--------------+---------------------------------------+
+|    0  AX650N                    V2.26.0 | 0000:05:00.0 |                175 MiB /      945 MiB |
+|   --   61C                      -- / -- | 0%        0% |               4301 MiB /     7040 MiB |
++-----------------------------------------+--------------+---------------------------------------+
+
++------------------------------------------------------------------------------------------------+
+| Processes:                                                                                     |
+| Card      PID  Process Name                                                   NPU Memory Usage |
+|================================================================================================|
+|    0    63118  /home/axera/samples/deepseek-r1-7b-gptq-int4/main_axcl_aarch64      4316448 KiB |
++------------------------------------------------------------------------------------------------+
+
+```