Transformers
DeepSeek-R1-Distill-Qwen-7B / run_deepseek-r1_7b_int4_axcl_aarch64.sh
wli1995's picture
Upload folder using huggingface_hub
815cf17 verified
raw
history blame contribute delete
441 Bytes
./main_axcl_aarch64 \
--template_filename_axmodel "deepseek-r1-7b-int4-ax650/qwen2_p128_l%d_together.axmodel" \
--axmodel_num 28 \
--url_tokenizer_model "http://127.0.0.1:12345" \
--filename_post_axmodel "deepseek-r1-7b-int4-ax650/qwen2_post.axmodel" \
--filename_tokens_embed "deepseek-r1-7b-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \
--tokens_embed_num 152064 \
--tokens_embed_size 3584 \
--use_mmap_load_embed 1 \
--live_print 1