ggufs commited on
Commit
8615809
·
verified ·
1 Parent(s): d9e2b11

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-VL-7B-Instruct
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.20.0
adapter_config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen2_5_VLForConditionalGeneration",
7
+ "parent_library": "transformers.models.qwen2_5_vl.modeling_qwen2_5_vl"
8
+ },
9
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 64,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.0,
25
+ "lora_ga_config": null,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "monteclora_config": null,
30
+ "peft_type": "LORA",
31
+ "peft_version": "0.20.0",
32
+ "qalora_group_size": 16,
33
+ "r": 32,
34
+ "rank_pattern": {},
35
+ "revision": null,
36
+ "target_modules": [
37
+ "layers.1.mlp.gate_proj",
38
+ "layers.25.mlp.gate_proj",
39
+ "layers.3.mlp.up_proj",
40
+ "layers.9.mlp.gate_proj",
41
+ "layers.4.mlp.down_proj",
42
+ "layers.21.mlp.gate_proj",
43
+ "layers.22.mlp.down_proj",
44
+ "layers.4.mlp.gate_proj",
45
+ "layers.23.mlp.up_proj",
46
+ "layers.18.mlp.gate_proj",
47
+ "layers.2.mlp.down_proj",
48
+ "layers.17.mlp.down_proj",
49
+ "layers.24.mlp.up_proj",
50
+ "layers.8.mlp.down_proj",
51
+ "q_proj",
52
+ "v_proj",
53
+ "layers.27.mlp.down_proj",
54
+ "layers.13.mlp.gate_proj",
55
+ "layers.21.mlp.down_proj",
56
+ "layers.23.mlp.gate_proj",
57
+ "layers.19.mlp.down_proj",
58
+ "layers.6.mlp.down_proj",
59
+ "layers.11.mlp.down_proj",
60
+ "layers.3.mlp.gate_proj",
61
+ "layers.8.mlp.up_proj",
62
+ "layers.12.mlp.up_proj",
63
+ "layers.1.mlp.up_proj",
64
+ "layers.26.mlp.down_proj",
65
+ "layers.19.mlp.gate_proj",
66
+ "layers.12.mlp.down_proj",
67
+ "layers.14.mlp.gate_proj",
68
+ "layers.22.mlp.gate_proj",
69
+ "layers.20.mlp.up_proj",
70
+ "layers.16.mlp.up_proj",
71
+ "layers.17.mlp.up_proj",
72
+ "layers.20.mlp.down_proj",
73
+ "layers.16.mlp.down_proj",
74
+ "layers.2.mlp.up_proj",
75
+ "layers.0.mlp.up_proj",
76
+ "k_proj",
77
+ "layers.3.mlp.down_proj",
78
+ "layers.16.mlp.gate_proj",
79
+ "layers.9.mlp.up_proj",
80
+ "layers.7.mlp.up_proj",
81
+ "layers.4.mlp.up_proj",
82
+ "layers.11.mlp.gate_proj",
83
+ "layers.19.mlp.up_proj",
84
+ "layers.7.mlp.gate_proj",
85
+ "layers.11.mlp.up_proj",
86
+ "layers.18.mlp.up_proj",
87
+ "layers.27.mlp.gate_proj",
88
+ "layers.25.mlp.down_proj",
89
+ "layers.7.mlp.down_proj",
90
+ "layers.15.mlp.gate_proj",
91
+ "layers.5.mlp.up_proj",
92
+ "layers.23.mlp.down_proj",
93
+ "layers.6.mlp.gate_proj",
94
+ "layers.20.mlp.gate_proj",
95
+ "layers.9.mlp.down_proj",
96
+ "layers.10.mlp.gate_proj",
97
+ "layers.15.mlp.up_proj",
98
+ "layers.0.mlp.down_proj",
99
+ "layers.2.mlp.gate_proj",
100
+ "layers.17.mlp.gate_proj",
101
+ "layers.24.mlp.gate_proj",
102
+ "o_proj",
103
+ "layers.10.mlp.down_proj",
104
+ "layers.13.mlp.up_proj",
105
+ "layers.14.mlp.down_proj",
106
+ "layers.13.mlp.down_proj",
107
+ "layers.22.mlp.up_proj",
108
+ "layers.26.mlp.gate_proj",
109
+ "layers.0.mlp.gate_proj",
110
+ "layers.5.mlp.gate_proj",
111
+ "layers.26.mlp.up_proj",
112
+ "layers.1.mlp.down_proj",
113
+ "layers.10.mlp.up_proj",
114
+ "layers.25.mlp.up_proj",
115
+ "layers.8.mlp.gate_proj",
116
+ "layers.24.mlp.down_proj",
117
+ "layers.21.mlp.up_proj",
118
+ "layers.27.mlp.up_proj",
119
+ "layers.14.mlp.up_proj",
120
+ "layers.6.mlp.up_proj",
121
+ "layers.15.mlp.down_proj",
122
+ "layers.5.mlp.down_proj",
123
+ "layers.12.mlp.gate_proj",
124
+ "layers.18.mlp.down_proj"
125
+ ],
126
+ "target_parameters": null,
127
+ "task_type": null,
128
+ "trainable_token_indices": null,
129
+ "use_bdlora": null,
130
+ "use_dora": false,
131
+ "use_qalora": false,
132
+ "use_rslora": false,
133
+ "velora_config": null
134
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7337ae29bd18ddb96864aec87603495e90085e463f50e20e801d88d2d0c8e2
3
+ size 323020048
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
processor_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 14,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 12845056,
24
+ "shortest_edge": 3136
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen2_5_VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": false,
35
+ "image_mean": [
36
+ 0.48145466,
37
+ 0.4578275,
38
+ 0.40821073
39
+ ],
40
+ "image_std": [
41
+ 0.26862954,
42
+ 0.26130258,
43
+ 0.27577711
44
+ ],
45
+ "max_frames": 768,
46
+ "merge_size": 2,
47
+ "min_frames": 4,
48
+ "patch_size": 14,
49
+ "resample": 3,
50
+ "rescale_factor": 0.00392156862745098,
51
+ "return_metadata": false,
52
+ "size": {
53
+ "longest_edge": 12845056,
54
+ "shortest_edge": 3136
55
+ },
56
+ "temporal_patch_size": 2,
57
+ "video_processor_type": "Qwen2VLVideoProcessor"
58
+ }
59
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "processor_class": "Qwen2_5_VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null
31
+ }