Hugging Face's logo

runanywhere
/
phi_tiny_moe_HNPU

Text Generation
hnpu
hexagon
npu
llm
v79
v81
Model card Files
xet
 Community
sanmonga22 commited on
Commit
b1b0f24
·
verified ·
1 Parent(s): e7a7bb5

Prune QHexRT HNPU bundle to runtime-minimum artifacts

Browse files

Remove 5 non-runtime/sensitive files from the QHexRT HNPU bundle.
Strip non-runtime _comment metadata from 2 manifest(s) without changing runtime fields.
Audit artifacts: QHexRT/hf_hnpu_audit cleanup plan, manifest reference check, and multi-agent review.

Files changed (7) hide show
  1. config.json +0 -7
  2. v79/phimoe.json +84 -85
  3. v79/special_tokens_map.json +0 -30
  4. v79/tokenizer_config.json +0 -130
  5. v81/phimoe.json +75 -76
  6. v81/special_tokens_map.json +0 -30
  7. v81/tokenizer_config.json +0 -130
config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "model_type": "qhexrt",
3
- "name": "phi_tiny_moe_HNPU",
4
- "framework": "qhexrt",
5
- "runtime": "qnn-htp",
6
- "_note": "Root config.json present so the Hugging Face Hub counts downloads (default query file for repos without a registered library)."
7
- }
 
 
 
 
 
 
 
 
v79/phimoe.json CHANGED
@@ -1,85 +1,84 @@
1
- {
2
- "schema_version": 1,
3
- "_comment": "phi-tiny-moe - Qualcomm Hexagon v79 (QHexRT) deployment manifest.",
4
- "model": {
5
- "name": "phi-tiny-moe",
6
- "family": "llm",
7
- "dsp_arch": "v79",
8
- "tokenizer_pre": "default"
9
- },
10
- "chat": {
11
- "user": {
12
- "prefix": [
13
- 32010
14
- ],
15
- "suffix": [
16
- 32007
17
- ]
18
- },
19
- "assistant": {
20
- "prefix": [
21
- 32001
22
- ],
23
- "suffix": [
24
- 32007
25
- ]
26
- }
27
- },
28
- "params": {
29
- "hidden": 4096,
30
- "vocab": 32064,
31
- "n_layers": 32,
32
- "max_ctx": 2048,
33
- "kv_dim": 512,
34
- "head_dim": 128,
35
- "rope_theta": 10000,
36
- "eos_token_id": 32000
37
- },
38
- "artifacts": {
39
- "contexts": {
40
- "a_lo": {
41
- "bin": "a_lo.bin"
42
- },
43
- "a_hi": {
44
- "bin": "a_hi.bin"
45
- },
46
- "ffn": {
47
- "bin": "ffn2.bin"
48
- },
49
- "lmhead": {
50
- "bin": "lmhead_ar1.bin"
51
- },
52
- "pf_lo": {
53
- "bin": "pf_lo.bin"
54
- },
55
- "pf_hi": {
56
- "bin": "pf_hi.bin"
57
- },
58
- "ffn_pf": {
59
- "bin": "ffn_pf.bin"
60
- }
61
- },
62
- "embed": "embed_f16.bin",
63
- "tokenizer": "tokenizer.json",
64
- "fixture_dir": "."
65
- },
66
- "plan": {
67
- "steps": [
68
- {
69
- "host": "phimoe_generate",
70
- "params": {
71
- "experts": "experts_i8.bin",
72
- "scales": "experts_scale.f32",
73
- "n_experts": 16,
74
- "ffn": 448,
75
- "jitter": 0.01,
76
- "neg": -50,
77
- "user_id": 32010,
78
- "end_id": 32007,
79
- "assistant_id": 32001,
80
- "max_new": 24
81
- }
82
- }
83
- ]
84
- }
85
- }
 
1
+ {
2
+ "schema_version": 1,
3
+ "model": {
4
+ "name": "phi-tiny-moe",
5
+ "family": "llm",
6
+ "dsp_arch": "v79",
7
+ "tokenizer_pre": "default"
8
+ },
9
+ "chat": {
10
+ "user": {
11
+ "prefix": [
12
+ 32010
13
+ ],
14
+ "suffix": [
15
+ 32007
16
+ ]
17
+ },
18
+ "assistant": {
19
+ "prefix": [
20
+ 32001
21
+ ],
22
+ "suffix": [
23
+ 32007
24
+ ]
25
+ }
26
+ },
27
+ "params": {
28
+ "hidden": 4096,
29
+ "vocab": 32064,
30
+ "n_layers": 32,
31
+ "max_ctx": 2048,
32
+ "kv_dim": 512,
33
+ "head_dim": 128,
34
+ "rope_theta": 10000,
35
+ "eos_token_id": 32000
36
+ },
37
+ "artifacts": {
38
+ "contexts": {
39
+ "a_lo": {
40
+ "bin": "a_lo.bin"
41
+ },
42
+ "a_hi": {
43
+ "bin": "a_hi.bin"
44
+ },
45
+ "ffn": {
46
+ "bin": "ffn2.bin"
47
+ },
48
+ "lmhead": {
49
+ "bin": "lmhead_ar1.bin"
50
+ },
51
+ "pf_lo": {
52
+ "bin": "pf_lo.bin"
53
+ },
54
+ "pf_hi": {
55
+ "bin": "pf_hi.bin"
56
+ },
57
+ "ffn_pf": {
58
+ "bin": "ffn_pf.bin"
59
+ }
60
+ },
61
+ "embed": "embed_f16.bin",
62
+ "tokenizer": "tokenizer.json",
63
+ "fixture_dir": "."
64
+ },
65
+ "plan": {
66
+ "steps": [
67
+ {
68
+ "host": "phimoe_generate",
69
+ "params": {
70
+ "experts": "experts_i8.bin",
71
+ "scales": "experts_scale.f32",
72
+ "n_experts": 16,
73
+ "ffn": 448,
74
+ "jitter": 0.01,
75
+ "neg": -50,
76
+ "user_id": 32010,
77
+ "end_id": 32007,
78
+ "assistant_id": 32001,
79
+ "max_new": 24
80
+ }
81
+ }
82
+ ]
83
+ }
84
+ }
 
v79/special_tokens_map.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
v79/tokenizer_config.json DELETED
@@ -1,130 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": true,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "32000": {
30
- "content": "<|endoftext|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "32001": {
38
- "content": "<|assistant|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": true,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "32002": {
46
- "content": "<|placeholder1|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|placeholder2|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|placeholder3|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|placeholder4|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": true,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "32006": {
78
- "content": "<|system|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|placeholder5|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|placeholder6|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": true,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "32010": {
110
- "content": "<|user|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": true,
114
- "single_word": false,
115
- "special": true
116
- }
117
- },
118
- "bos_token": "<s>",
119
- "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
120
- "clean_up_tokenization_spaces": false,
121
- "eos_token": "<|endoftext|>",
122
- "legacy": false,
123
- "model_max_length": 4096,
124
- "pad_token": "<|endoftext|>",
125
- "padding_side": "left",
126
- "sp_model_kwargs": {},
127
- "tokenizer_class": "LlamaTokenizer",
128
- "unk_token": "<unk>",
129
- "use_default_system_prompt": false
130
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
v81/phimoe.json CHANGED
@@ -1,76 +1,75 @@
1
- {
2
- "schema_version": 1,
3
- "_comment": "phi-tiny-moe - Qualcomm Hexagon v81 (QHexRT) deployment manifest.",
4
- "model": {
5
- "name": "phi-tiny-moe",
6
- "family": "llm",
7
- "dsp_arch": "v81",
8
- "tokenizer_pre": "default"
9
- },
10
- "chat": {
11
- "user": {
12
- "prefix": [
13
- 32010
14
- ],
15
- "suffix": [
16
- 32007
17
- ]
18
- },
19
- "assistant": {
20
- "prefix": [
21
- 32001
22
- ],
23
- "suffix": [
24
- 32007
25
- ]
26
- }
27
- },
28
- "params": {
29
- "hidden": 4096,
30
- "vocab": 32064,
31
- "n_layers": 32,
32
- "max_ctx": 2048,
33
- "kv_dim": 512,
34
- "head_dim": 128,
35
- "rope_theta": 10000,
36
- "eos_token_id": 32000
37
- },
38
- "artifacts": {
39
- "contexts": {
40
- "a_lo": {
41
- "bin": "a_lo.bin"
42
- },
43
- "a_hi": {
44
- "bin": "a_hi.bin"
45
- },
46
- "ffn": {
47
- "bin": "ffn2.bin"
48
- },
49
- "lmhead": {
50
- "bin": "lmhead_ar1.bin"
51
- }
52
- },
53
- "embed": "embed_f16.bin",
54
- "tokenizer": "tokenizer.json",
55
- "fixture_dir": "."
56
- },
57
- "plan": {
58
- "steps": [
59
- {
60
- "host": "phimoe_generate",
61
- "params": {
62
- "experts": "experts_i8.bin",
63
- "scales": "experts_scale.f32",
64
- "n_experts": 16,
65
- "ffn": 448,
66
- "jitter": 0.01,
67
- "neg": -50,
68
- "user_id": 32010,
69
- "end_id": 32007,
70
- "assistant_id": 32001,
71
- "max_new": 24
72
- }
73
- }
74
- ]
75
- }
76
- }
 
1
+ {
2
+ "schema_version": 1,
3
+ "model": {
4
+ "name": "phi-tiny-moe",
5
+ "family": "llm",
6
+ "dsp_arch": "v81",
7
+ "tokenizer_pre": "default"
8
+ },
9
+ "chat": {
10
+ "user": {
11
+ "prefix": [
12
+ 32010
13
+ ],
14
+ "suffix": [
15
+ 32007
16
+ ]
17
+ },
18
+ "assistant": {
19
+ "prefix": [
20
+ 32001
21
+ ],
22
+ "suffix": [
23
+ 32007
24
+ ]
25
+ }
26
+ },
27
+ "params": {
28
+ "hidden": 4096,
29
+ "vocab": 32064,
30
+ "n_layers": 32,
31
+ "max_ctx": 2048,
32
+ "kv_dim": 512,
33
+ "head_dim": 128,
34
+ "rope_theta": 10000,
35
+ "eos_token_id": 32000
36
+ },
37
+ "artifacts": {
38
+ "contexts": {
39
+ "a_lo": {
40
+ "bin": "a_lo.bin"
41
+ },
42
+ "a_hi": {
43
+ "bin": "a_hi.bin"
44
+ },
45
+ "ffn": {
46
+ "bin": "ffn2.bin"
47
+ },
48
+ "lmhead": {
49
+ "bin": "lmhead_ar1.bin"
50
+ }
51
+ },
52
+ "embed": "embed_f16.bin",
53
+ "tokenizer": "tokenizer.json",
54
+ "fixture_dir": "."
55
+ },
56
+ "plan": {
57
+ "steps": [
58
+ {
59
+ "host": "phimoe_generate",
60
+ "params": {
61
+ "experts": "experts_i8.bin",
62
+ "scales": "experts_scale.f32",
63
+ "n_experts": 16,
64
+ "ffn": 448,
65
+ "jitter": 0.01,
66
+ "neg": -50,
67
+ "user_id": 32010,
68
+ "end_id": 32007,
69
+ "assistant_id": 32001,
70
+ "max_new": 24
71
+ }
72
+ }
73
+ ]
74
+ }
75
+ }
 
v81/special_tokens_map.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
v81/tokenizer_config.json DELETED
@@ -1,130 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": true,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "32000": {
30
- "content": "<|endoftext|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "32001": {
38
- "content": "<|assistant|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": true,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "32002": {
46
- "content": "<|placeholder1|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|placeholder2|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|placeholder3|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|placeholder4|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": true,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "32006": {
78
- "content": "<|system|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|placeholder5|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|placeholder6|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": true,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "32010": {
110
- "content": "<|user|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": true,
114
- "single_word": false,
115
- "special": true
116
- }
117
- },
118
- "bos_token": "<s>",
119
- "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
120
- "clean_up_tokenization_spaces": false,
121
- "eos_token": "<|endoftext|>",
122
- "legacy": false,
123
- "model_max_length": 4096,
124
- "pad_token": "<|endoftext|>",
125
- "padding_side": "left",
126
- "sp_model_kwargs": {},
127
- "tokenizer_class": "LlamaTokenizer",
128
- "unk_token": "<unk>",
129
- "use_default_system_prompt": false
130
- }