cyrilvallez HF staff commited on
Commit
3a7cb2e
·
verified ·
1 Parent(s): 28148ed

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/tool_call|>": 200026,
3
+ "<|/tool|>": 200024,
4
+ "<|assistant|>": 200019,
5
+ "<|end|>": 200020,
6
+ "<|system|>": 200022,
7
+ "<|tag|>": 200028,
8
+ "<|tool_call|>": 200025,
9
+ "<|tool_response|>": 200027,
10
+ "<|tool|>": 200023,
11
+ "<|user|>": 200021
12
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,185 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi4MultimodalForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "audio_config": {
8
+ "activation": "swish",
9
+ "audio_token_id": 200011,
10
+ "bias_max_distance": 500,
11
+ "bias_symmetric": false,
12
+ "chunk_size": -1,
13
+ "conv_activation": "swish",
14
+ "conv_glu_type": "swish",
15
+ "depthwise_multiplier": 1,
16
+ "depthwise_seperable_out_channel": 1024,
17
+ "downsample_rate": 1,
18
+ "dropout_rate": 0.0,
19
+ "ext_pw_out_channel": 1024,
20
+ "feature_layer": -2,
21
+ "hidden_size": 1024,
22
+ "initializer_range": 0.02,
23
+ "input_size": 80,
24
+ "intermediate_size": 1536,
25
+ "kernel_size": 3,
26
+ "left_chunk": 18,
27
+ "model_type": "phi4_multimodal_audio",
28
+ "nemo_activation": "relu",
29
+ "nemo_conv_channels": 1024,
30
+ "nemo_final_size": 10,
31
+ "num_attention_heads": 16,
32
+ "num_blocks": 24,
33
+ "time_reduction": 8
34
+ },
35
+ "bos_token_id": 199999,
36
+ "embd_pdrop": 0.0,
37
+ "eos_token_id": [
38
+ 199999,
39
+ 200020
40
+ ],
41
+ "full_attn_mod": 1,
42
+ "hidden_act": "silu",
43
+ "hidden_size": 3072,
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 8192,
46
+ "interpolate_factor": 1,
47
+ "lm_head_bias": false,
48
+ "max_position_embeddings": 131072,
49
+ "mlp_bias": false,
50
+ "model_type": "phi4_multimodal",
51
+ "num_attention_heads": 24,
52
+ "num_hidden_layers": 32,
53
+ "num_key_value_heads": 8,
54
+ "original_max_position_embeddings": 4096,
55
+ "pad_token_id": 199999,
56
+ "partial_rotary_factor": 0.75,
57
+ "resid_pdrop": 0.0,
58
+ "rms_norm_eps": 1e-05,
59
+ "rope_scaling": {
60
+ "long_factor": [
61
+ 1,
62
+ 1.118320672,
63
+ 1.250641126,
64
+ 1.398617824,
65
+ 1.564103225,
66
+ 1.74916897,
67
+ 1.956131817,
68
+ 2.187582649,
69
+ 2.446418898,
70
+ 2.735880826,
71
+ 3.059592084,
72
+ 3.421605075,
73
+ 3.826451687,
74
+ 4.279200023,
75
+ 4.785517845,
76
+ 5.351743533,
77
+ 5.984965424,
78
+ 6.693110555,
79
+ 7.485043894,
80
+ 8.370679318,
81
+ 9.36110372,
82
+ 10.4687158,
83
+ 11.70738129,
84
+ 13.09260651,
85
+ 14.64173252,
86
+ 16.37415215,
87
+ 18.31155283,
88
+ 20.47818807,
89
+ 22.90118105,
90
+ 25.61086418,
91
+ 28.64115884,
92
+ 32.03,
93
+ 32.1,
94
+ 32.13,
95
+ 32.23,
96
+ 32.6,
97
+ 32.61,
98
+ 32.64,
99
+ 32.66,
100
+ 32.7,
101
+ 32.71,
102
+ 32.93,
103
+ 32.97,
104
+ 33.28,
105
+ 33.49,
106
+ 33.5,
107
+ 44.16,
108
+ 47.77
109
+ ],
110
+ "short_factor": [
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0,
133
+ 1.0,
134
+ 1.0,
135
+ 1.0,
136
+ 1.0,
137
+ 1.0,
138
+ 1.0,
139
+ 1.0,
140
+ 1.0,
141
+ 1.0,
142
+ 1.0,
143
+ 1.0,
144
+ 1.0,
145
+ 1.0,
146
+ 1.0,
147
+ 1.0,
148
+ 1.0,
149
+ 1.0,
150
+ 1.0,
151
+ 1.0,
152
+ 1.0,
153
+ 1.0,
154
+ 1.0,
155
+ 1.0,
156
+ 1.0,
157
+ 1.0,
158
+ 1.0
159
+ ],
160
+ "type": "longrope"
161
+ },
162
+ "rope_theta": 10000.0,
163
+ "sliding_window": 262144,
164
+ "tie_word_embeddings": true,
165
+ "torch_dtype": "bfloat16",
166
+ "transformers_version": "4.51.0.dev0",
167
+ "use_cache": true,
168
+ "vision_config": {
169
+ "attention_dropout": 0.0,
170
+ "crop_size": 448,
171
+ "feature_layer": -2,
172
+ "hidden_act": "gelu_pytorch_tanh",
173
+ "hidden_size": 1152,
174
+ "image_size": 448,
175
+ "image_token_id": 200010,
176
+ "intermediate_size": 4304,
177
+ "layer_norm_eps": 1e-06,
178
+ "model_type": "phi4_multimodal_vision",
179
+ "num_attention_heads": 16,
180
+ "num_channels": 3,
181
+ "num_hidden_layers": 27,
182
+ "patch_size": 14
183
+ },
184
+ "vocab_size": 200064
185
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 199999,
6
+ 200020
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.51.0.dev0"
10
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b93f5d0c9422c0b76b68119660187989bd8bb47848994376be3ac53eb61a95
3
+ size 4903637712
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6f60df08041b5c48afe7d7624d4de6e9d7d86162dec7a7e908a71d595e2967
3
+ size 4584575136
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_compression_rate": 8,
3
+ "audio_downsample_rate": 1,
4
+ "audio_feat_stride": 1,
5
+ "dynamic_hd": 36,
6
+ "feature_extractor_type": "Phi4MultimodalFeatureExtractor",
7
+ "feature_size": 80,
8
+ "hop_length": 160,
9
+ "image_processor_type": "Phi4MMImageProcessor",
10
+ "n_fft": 512,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "preemphasis": 0.97,
14
+ "processor_class": "Phi4MultimodalProcessor",
15
+ "return_attention_mask": true,
16
+ "sampling_rate": 16000,
17
+ "win_length": 400
18
+ }
processor_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "fake_audio_token_pattern": "<\\|audio_\\d+\\|>",
3
+ "fake_image_token_pattern": "<\\|image_\\d+\\|>",
4
+ "processor_class": "Phi4MultimodalProcessor"
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
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": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapter_config.json → speech-lora/adapter_config.json RENAMED
File without changes
adapter_model.safetensors → speech-lora/adapter_model.safetensors RENAMED
File without changes
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1b9f641d4f8b7247b8d5007dd3b6a9f6a87cb5123134fe0d326f14d10c0585
3
+ size 15524479
tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "199999": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "200010": {
13
+ "content": "<|endoftext10|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "200011": {
21
+ "content": "<|endoftext11|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "200018": {
29
+ "content": "<|endofprompt|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "200019": {
37
+ "content": "<|assistant|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "200020": {
45
+ "content": "<|end|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "200021": {
53
+ "content": "<|user|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "200022": {
61
+ "content": "<|system|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "200023": {
69
+ "content": "<|tool|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "200024": {
77
+ "content": "<|/tool|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "200025": {
85
+ "content": "<|tool_call|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "200026": {
93
+ "content": "<|/tool_call|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "200027": {
101
+ "content": "<|tool_response|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "200028": {
109
+ "content": "<|tag|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "audio_token": "<|endoftext11|>",
118
+ "bos_token": "<|endoftext|>",
119
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {
123
+ "audio_token": "<|endoftext11|>",
124
+ "image_token": "<|endoftext10|>"
125
+ },
126
+ "image_token": "<|endoftext10|>",
127
+ "model_max_length": 131072,
128
+ "pad_token": "<|endoftext|>",
129
+ "processor_class": "Phi4MultimodalProcessor",
130
+ "tokenizer_class": "GPT2Tokenizer",
131
+ "unk_token": "<|endoftext|>"
132
+ }
vision-lora/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": false,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 512,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.0,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 256,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": "model.layers.\\d+.((self_attn.(qkv|o)_proj)|(mlp.(gate_up|down)_proj))",
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
vision-lora/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76facf464ca0246e9f5dc409520e83764e0b73fa66fdb561526e064133728f8a
3
+ size 738228552
vocab.json ADDED
The diff for this file is too large to render. See raw diff