|
|
./main_axcl_x86 \ |
|
|
--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \ |
|
|
--template_filename_axmodel "qwen2.5-3b-gptq-int4-ctx-ax650/qwen2_p128_l%d_together.axmodel" \ |
|
|
--axmodel_num 36 \ |
|
|
--tokenizer_type 2 \ |
|
|
--url_tokenizer_model "http://127.0.0.1:12345" \ |
|
|
--filename_post_axmodel "qwen2.5-3b-gptq-int4-ctx-ax650/qwen2_post.axmodel" \ |
|
|
--filename_tokens_embed "qwen2.5-3b-gptq-int4-ctx-ax650/model.embed_tokens.weight.bfloat16.bin" \ |
|
|
--tokens_embed_num 151936 \ |
|
|
--tokens_embed_size 2048 \ |
|
|
--use_mmap_load_embed 0 \ |
|
|
--live_print 1 \ |
|
|
--devices 0 |
|
|
|
|
|
|
|
|
|
