qqc1989 commited on
Commit
52a7560
·
verified ·
1 Parent(s): 88dd66b

Upload 11 files

Browse files
.gitattributes CHANGED
@@ -38,3 +38,6 @@ main_api filter=lfs diff=lfs merge=lfs -text
38
  main_ax650 filter=lfs diff=lfs merge=lfs -text
39
  main_axcl_aarch64 filter=lfs diff=lfs merge=lfs -text
40
  main_axcl_x86 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
38
  main_ax650 filter=lfs diff=lfs merge=lfs -text
39
  main_axcl_aarch64 filter=lfs diff=lfs merge=lfs -text
40
  main_axcl_x86 filter=lfs diff=lfs merge=lfs -text
41
+ main_api_ax650 filter=lfs diff=lfs merge=lfs -text
42
+ main_api_axcl_aarch64 filter=lfs diff=lfs merge=lfs -text
43
+ main_api_axcl_x86 filter=lfs diff=lfs merge=lfs -text
main_api_ax650 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53024db31c1fe910d5b13f3e31daf903bfde87ee18d29d49a4094aadb883517f
3
+ size 1064648
main_api_axcl_aarch64 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff939d9a02d8aa96f78e62af9d5d146f8d8e8b7f20628cbb260cbaf990549547
3
+ size 1868088
main_api_axcl_x86 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdd3551f41aa43fbd91bf307901398a49372f9ddf6a7e027f7409229bbef468
3
+ size 1913024
main_ax650 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:870254b83b53d8f1909a03d2e73b0049fd5541e848579fc530888d07c28a48a2
3
- size 989368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622b8f33f3d6e9caf0b5aac480a5327d5f92b419d717b7403cb72807fa1e3fc7
3
+ size 985248
main_axcl_aarch64 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03012513d42b834360fac6e61aa8b7387deb4f5ecd9f9c86d0b208e608b8c991
3
- size 1724632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a587bcc25917e4c66277fba689a0e2718f50103e0fd249729e0cfb2f9b1d7c83
3
+ size 1787328
main_axcl_x86 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f872d9f2238ec7db7ce3a075d52a673bac7b5a7e18455a81852b80223037ae3
3
- size 1839824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a177ef35fc8ad418b92077d08338004325c4d6a36ad17de66cf64ba9b6172393
3
+ size 1844336
post_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "enable_temperature" : false,
3
  "temperature" : 0.9,
4
 
5
  "enable_repetition_penalty" : false,
@@ -9,6 +9,6 @@
9
  "enable_top_p_sampling" : false,
10
  "top_p" : 0.8,
11
 
12
- "enable_top_k_sampling" : false,
13
  "top_k" : 10
14
  }
 
1
  {
2
+ "enable_temperature" : true,
3
  "temperature" : 0.9,
4
 
5
  "enable_repetition_penalty" : false,
 
9
  "enable_top_p_sampling" : false,
10
  "top_p" : 0.8,
11
 
12
+ "enable_top_k_sampling" : true,
13
  "top_k" : 10
14
  }
run_qwen2.5_7b_ctx_ax650.sh CHANGED
@@ -1,7 +1,6 @@
1
  ./main_ax650 \
2
  --template_filename_axmodel "qwen2.5-7b-ctx-ax650/qwen2_p128_l%d_together.axmodel" \
3
  --axmodel_num 28 \
4
- --tokenizer_type 2 \
5
  --url_tokenizer_model "http://0.0.0.0:12345" \
6
  --filename_post_axmodel "qwen2.5-7b-ctx-ax650/qwen2_post.axmodel" \
7
  --filename_tokens_embed "qwen2.5-7b-ctx-ax650/model.embed_tokens.weight.bfloat16.bin" \
 
1
  ./main_ax650 \
2
  --template_filename_axmodel "qwen2.5-7b-ctx-ax650/qwen2_p128_l%d_together.axmodel" \
3
  --axmodel_num 28 \
 
4
  --url_tokenizer_model "http://0.0.0.0:12345" \
5
  --filename_post_axmodel "qwen2.5-7b-ctx-ax650/qwen2_post.axmodel" \
6
  --filename_tokens_embed "qwen2.5-7b-ctx-ax650/model.embed_tokens.weight.bfloat16.bin" \
run_qwen2.5_7b_ctx_int4_ax650.sh CHANGED
@@ -1,10 +1,8 @@
1
  ./main_ax650 \
2
  --template_filename_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_p128_l%d_together.axmodel" \
3
- --axmodel_num 28 \
4
- --tokenizer_type 2 \
5
  --url_tokenizer_model "http://0.0.0.0:12345" \
6
  --filename_post_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_post.axmodel" \
7
- --filename_tokens_embed "qwen2.5-7b-ctx-ax650/model.embed_tokens.weight.bfloat16.bin" \
8
  --tokens_embed_num 152064 \
9
  --tokens_embed_size 3584 \
10
  --use_mmap_load_embed 1 \
 
1
  ./main_ax650 \
2
  --template_filename_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_p128_l%d_together.axmodel" \
 
 
3
  --url_tokenizer_model "http://0.0.0.0:12345" \
4
  --filename_post_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_post.axmodel" \
5
+ --filename_tokens_embed "qwen2.5-7b-ctx-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \
6
  --tokens_embed_num 152064 \
7
  --tokens_embed_size 3584 \
8
  --use_mmap_load_embed 1 \
run_qwen2.5_7b_ctx_int4_axcl_aarch64.sh ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ./main_axcl_aarch64 \
2
+ --template_filename_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_p128_l%d_together.axmodel" \
3
+ --axmodel_num 28 \
4
+ --url_tokenizer_model "http://0.0.0.0:12345" \
5
+ --filename_post_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_post.axmodel" \
6
+ --filename_tokens_embed "qwen2.5-7b-ctx-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \
7
+ --tokens_embed_num 152064 \
8
+ --tokens_embed_size 3584 \
9
+ --use_mmap_load_embed 1 \
10
+ --live_print 1 \
11
+ --devices 0
12
+
13
+
14
+ #--system_prompt "你的名字叫小智(allen),你是一个人畜无害的AI助手。深圳市今天(4月1日)阴天,愚人节,气温在14°C至19°C之间,微风。" \
15
+ #--kvcache_path "./kvcache" \
16
+
run_qwen2.5_7b_ctx_int4_axcl_x86.sh ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ./main_axcl_aarch64 \
2
+ --template_filename_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_p128_l%d_together.axmodel" \
3
+ --axmodel_num 28 \
4
+ --url_tokenizer_model "http://0.0.0.0:12345" \
5
+ --filename_post_axmodel "qwen2.5-7b-ctx-int4-ax650/qwen2_post.axmodel" \
6
+ --filename_tokens_embed "qwen2.5-7b-ctx-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \
7
+ --tokens_embed_num 152064 \
8
+ --tokens_embed_size 3584 \
9
+ --use_mmap_load_embed 1 \
10
+ --live_print 1 \
11
+ --devices 0
12
+
13
+
14
+ #--system_prompt "你的名字叫小智(allen),你是一个人畜无害的AI助手。深圳市今天(4月1日)阴天,愚人节,气温在14°C至19°C之间,微风。" \
15
+ #--kvcache_path "./kvcache" \
16
+