This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
|
products:sbc:edge-2l:npu:deepseek-r1-distill-qwen-1.5b-7b [2026/03/31 06:03] william created |
products:sbc:edge-2l:npu:deepseek-r1-distill-qwen-1.5b-7b [2026/05/11 02:52] (current) nick ↷ Page moved from local:users:william:debug:edge2l:deepseek-r1-distill-qwen-1.5b-7b to products:sbc:edge-2l:npu:deepseek-r1-distill-qwen-1.5b-7b |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ====== Large Model - DeepSeek-R1-Distill-Qwen-1.5B/ | ====== Large Model - DeepSeek-R1-Distill-Qwen-1.5B/ | ||
| + | |||
| + | This guide introduces how to run the DeepSeek-R1-Distill-Qwen-1.5B and DeepSeek-R1-Distill-Qwen-7B large language models on the Edge2L SBC.\\ | ||
| + | |||
| + | ==== Download the models and code ==== | ||
| The version information we are using is as follows: \\ | The version information we are using is as follows: \\ | ||
| + | OS:Ubuntu 24.04 \\ | ||
| rknn-llm: release-v1.2.3 \\ | rknn-llm: release-v1.2.3 \\ | ||
| Line 21: | Line 26: | ||
| - | ==== Compile ==== | + | ==== Compile |
| Modify '' | Modify '' | ||
| Line 46: | Line 51: | ||
| ``` | ``` | ||
| - | ==== Run ==== | + | ==== Run the program |
| Place the model file DeepSeek-R1-Distill-Qwen-1.5B_W4A16_RK3576.rkllm or DeepSeek-R1-Distill-Qwen-7B_W4A16_RK3576.rkllm into the demo_Linux_aarch64 directory. | Place the model file DeepSeek-R1-Distill-Qwen-1.5B_W4A16_RK3576.rkllm or DeepSeek-R1-Distill-Qwen-7B_W4A16_RK3576.rkllm into the demo_Linux_aarch64 directory. | ||
| Line 53: | Line 58: | ||
| $ cd install/ | $ cd install/ | ||
| $ export LD_LIBRARY_PATH=./ | $ export LD_LIBRARY_PATH=./ | ||
| - | $ export RKLLM_LOG_LEVEL=1 | + | $ export RKLLM_LOG_LEVEL=1 |
| $ ./llm_demo ./ | $ ./llm_demo ./ | ||
| ``` | ``` | ||
| + | {{local: | ||