Skip to content

Commit b0357d0

Browse files
committed
Merge branch 'dev' of github.com:m5stack/StackFlow into dev
2 parents c723e3a + d3a699f commit b0357d0

22 files changed

Lines changed: 677 additions & 7 deletions

projects/llm_framework/main_llm/mode_deepseek-r1-1.5B-ax630c.json renamed to projects/llm_framework/main_llm/models/mode_deepseek-r1-1.5B-ax630c.json

File renamed without changes.
Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
{
2+
"mode":"deepseek-r1-1.5B-p256-ax630c",
3+
"type":"llm",
4+
"capabilities":[
5+
"text_generation",
6+
"chat"
7+
],
8+
"input_type":[
9+
"llm.utf-8",
10+
"llm.utf-8.stream",
11+
"llm.chat_completion",
12+
"llm.chat_completion.stream"
13+
],
14+
"output_type":[
15+
"llm.utf-8",
16+
"llm.utf-8.stream"
17+
],
18+
"mode_param":{
19+
"tokenizer_type":2,
20+
"filename_tokenizer_model":"http://localhost:8080",
21+
"filename_tokens_embed":"model.embed_tokens.weight.bfloat16.bin",
22+
"filename_post_axmodel":"qwen2_post.axmodel",
23+
"template_filename_axmodel":"qwen2_p256_l%d_together.axmodel",
24+
"b_use_topk":false,
25+
"b_bos":false,
26+
"b_eos":false,
27+
"axmodel_num":28,
28+
"tokens_embed_num":151936,
29+
"tokens_embed_size":1536,
30+
"b_use_mmap_load_embed":true,
31+
"b_dynamic_load_axmodel_layer":false,
32+
"ext_scripts":["tokenizer_deepseek-r1-1.5B-p256-ax630c.py"]
33+
}
34+
}
Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
{
2+
"mode":"llama3.2-1B-p256-ax630c",
3+
"type":"llm",
4+
"capabilities":[
5+
"text_generation",
6+
"chat"
7+
],
8+
"input_type":[
9+
"llm.utf-8",
10+
"llm.utf-8.stream",
11+
"llm.chat_completion",
12+
"llm.chat_completion.stream"
13+
],
14+
"output_type":[
15+
"llm.utf-8",
16+
"llm.utf-8.stream"
17+
],
18+
"mode_param":{
19+
"tokenizer_type":2,
20+
"filename_tokenizer_model":"http://localhost:8080",
21+
"filename_tokens_embed":"model.embed_tokens.weight.bfloat16.bin",
22+
"filename_post_axmodel":"llama_post.axmodel",
23+
"template_filename_axmodel":"llama_p256_l%d_together.axmodel",
24+
"b_use_topk":false,
25+
"b_bos":false,
26+
"b_eos":false,
27+
"axmodel_num":16,
28+
"tokens_embed_num":128256,
29+
"tokens_embed_size":2048,
30+
"b_use_mmap_load_embed":true,
31+
"b_dynamic_load_axmodel_layer":false,
32+
"ext_scripts":["tokenizer_llama3.2-1B-p256-ax630c.py"]
33+
}
34+
}

projects/llm_framework/main_llm/mode_llama3.2-1B-prefill-ax630c.json renamed to projects/llm_framework/main_llm/models/mode_llama3.2-1B-prefill-ax630c.json

File renamed without changes.

projects/llm_framework/main_llm/mode_openbuddy-llama3.2-1B-ax630c.json renamed to projects/llm_framework/main_llm/models/mode_openbuddy-llama3.2-1B-ax630c.json

File renamed without changes.
Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
{
2+
"mode":"qwen2.5-0.5B-p256-ax630c",
3+
"type":"llm",
4+
"capabilities":[
5+
"text_generation",
6+
"chat"
7+
],
8+
"input_type":[
9+
"llm.utf-8",
10+
"llm.utf-8.stream",
11+
"llm.chat_completion",
12+
"llm.chat_completion.stream"
13+
],
14+
"output_type":[
15+
"llm.utf-8",
16+
"llm.utf-8.stream"
17+
],
18+
"mode_param":{
19+
"tokenizer_type":2,
20+
"filename_tokenizer_model":"http://localhost:8080",
21+
"filename_tokens_embed":"model.embed_tokens.weight.bfloat16.bin",
22+
"filename_post_axmodel":"qwen2_post.axmodel",
23+
"template_filename_axmodel":"qwen2_p256_l%d_together.axmodel",
24+
"b_use_topk":false,
25+
"b_bos":false,
26+
"b_eos":false,
27+
"axmodel_num":24,
28+
"tokens_embed_num":151936,
29+
"tokens_embed_size":896,
30+
"b_use_mmap_load_embed":true,
31+
"b_dynamic_load_axmodel_layer":false,
32+
"ext_scripts":["tokenizer_qwen2.5-0.5B-p256-ax630c.py"]
33+
}
34+
}

projects/llm_framework/main_llm/mode_qwen2.5-0.5B-prefill-20e.json renamed to projects/llm_framework/main_llm/models/mode_qwen2.5-0.5B-prefill-20e.json

File renamed without changes.

projects/llm_framework/main_llm/mode_qwen2.5-1.5B-ax630c.json renamed to projects/llm_framework/main_llm/models/mode_qwen2.5-1.5B-ax630c.json

File renamed without changes.
Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
{
2+
"mode":"qwen2.5-1.5B-p256-ax630c",
3+
"type":"llm",
4+
"capabilities":[
5+
"text_generation",
6+
"chat"
7+
],
8+
"input_type":[
9+
"llm.utf-8",
10+
"llm.utf-8.stream",
11+
"llm.chat_completion",
12+
"llm.chat_completion.stream"
13+
],
14+
"output_type":[
15+
"llm.utf-8",
16+
"llm.utf-8.stream"
17+
],
18+
"mode_param":{
19+
"tokenizer_type":2,
20+
"filename_tokenizer_model":"http://localhost:8080",
21+
"filename_tokens_embed":"model.embed_tokens.weight.bfloat16.bin",
22+
"filename_post_axmodel":"qwen2_post.axmodel",
23+
"template_filename_axmodel":"qwen2_p256_l%d_together.axmodel",
24+
"b_use_topk":false,
25+
"b_bos":false,
26+
"b_eos":false,
27+
"axmodel_num":28,
28+
"tokens_embed_num":151936,
29+
"tokens_embed_size":1536,
30+
"b_use_mmap_load_embed":true,
31+
"b_dynamic_load_axmodel_layer":false,
32+
"ext_scripts":["tokenizer_qwen2.5-1.5B-p256-ax630c.py"]
33+
}
34+
}

projects/llm_framework/main_llm/mode_qwen2.5-coder-0.5B-ax630c.json renamed to projects/llm_framework/main_llm/models/mode_qwen2.5-coder-0.5B-ax630c.json

File renamed without changes.

0 commit comments

Comments
 (0)