srai86825 commited on
Commit
6dbb223
·
verified ·
1 Parent(s): 4be47a2

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ checkpoint-3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # Qwen2.5-VL-32B Tool Assistant with LoRA fine-tuning
3
+
4
+ This is a LoRA adapter for the Qwen2.5-VL-32B model, fine-tuned for tool-use with visual input.
5
+
6
+ ## Usage
7
+
8
+ ```python
9
+ from transformers import AutoProcessor, AutoModelForCausalLM
10
+ from peft import PeftModel
11
+ import torch
12
+ from PIL import Image
13
+
14
+ # Load the model
15
+ processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-32B-Instruct")
16
+ base_model = AutoModelForCausalLM.from_pretrained(
17
+ "Qwen/Qwen2.5-VL-32B-Instruct",
18
+ torch_dtype=torch.bfloat16,
19
+ device_map="auto",
20
+ trust_remote_code=True
21
+ )
22
+ model = PeftModel.from_pretrained(
23
+ base_model,
24
+ "srai86825/qwen-vl-tool-assistant-lora"
25
+ )
26
+
27
+ # Use the model
28
+ image = Image.open("your_image.jpg")
29
+ text = "What is in this image?"
30
+
31
+ inputs = processor(text=text, images=image, return_tensors="pt").to("cuda")
32
+ outputs = model.generate(**inputs, max_new_tokens=100)
33
+ result = processor.decode(outputs[0], skip_special_tokens=True)
34
+ print(result)
35
+ ```
36
+
37
+ ## Training Details
38
+ - Base model: Qwen/Qwen2.5-VL-32B-Instruct
39
+ - Fine-tuning method: LoRA with rank 8
40
+ - Target modules: all
41
+ - Training data: Custom tool-use dataset
adapter_config.json ADDED
@@ -0,0 +1,228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-32B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "33.mlp.down_proj",
28
+ "59.mlp.gate_proj",
29
+ "layers.19.mlp.gate_proj",
30
+ "layers.6.mlp.up_proj",
31
+ "layers.21.mlp.up_proj",
32
+ "37.mlp.down_proj",
33
+ "52.mlp.down_proj",
34
+ "60.mlp.gate_proj",
35
+ "layers.3.mlp.up_proj",
36
+ "37.mlp.up_proj",
37
+ "47.mlp.up_proj",
38
+ "62.mlp.up_proj",
39
+ "layers.12.mlp.down_proj",
40
+ "50.mlp.down_proj",
41
+ "layers.3.mlp.down_proj",
42
+ "layers.7.mlp.up_proj",
43
+ "55.mlp.up_proj",
44
+ "57.mlp.down_proj",
45
+ "layers.14.mlp.down_proj",
46
+ "layers.24.mlp.down_proj",
47
+ "58.mlp.up_proj",
48
+ "layers.21.mlp.gate_proj",
49
+ "42.mlp.up_proj",
50
+ "layers.30.mlp.up_proj",
51
+ "layers.6.mlp.gate_proj",
52
+ "56.mlp.gate_proj",
53
+ "56.mlp.down_proj",
54
+ "49.mlp.up_proj",
55
+ "layers.29.mlp.down_proj",
56
+ "q_proj",
57
+ "55.mlp.down_proj",
58
+ "layers.14.mlp.gate_proj",
59
+ "layers.16.mlp.gate_proj",
60
+ "51.mlp.up_proj",
61
+ "layers.10.mlp.gate_proj",
62
+ "45.mlp.gate_proj",
63
+ "layers.25.mlp.up_proj",
64
+ "layers.13.mlp.gate_proj",
65
+ "layers.24.mlp.gate_proj",
66
+ "41.mlp.up_proj",
67
+ "45.mlp.down_proj",
68
+ "41.mlp.gate_proj",
69
+ "48.mlp.down_proj",
70
+ "layers.28.mlp.down_proj",
71
+ "layers.18.mlp.down_proj",
72
+ "33.mlp.gate_proj",
73
+ "36.mlp.up_proj",
74
+ "layers.1.mlp.down_proj",
75
+ "layers.0.mlp.gate_proj",
76
+ "63.mlp.down_proj",
77
+ "layers.15.mlp.down_proj",
78
+ "40.mlp.up_proj",
79
+ "layers.0.mlp.up_proj",
80
+ "layers.4.mlp.down_proj",
81
+ "32.mlp.down_proj",
82
+ "42.mlp.down_proj",
83
+ "layers.7.mlp.gate_proj",
84
+ "layers.22.mlp.gate_proj",
85
+ "layers.18.mlp.gate_proj",
86
+ "layers.8.mlp.up_proj",
87
+ "39.mlp.up_proj",
88
+ "layers.16.mlp.down_proj",
89
+ "49.mlp.down_proj",
90
+ "62.mlp.gate_proj",
91
+ "54.mlp.up_proj",
92
+ "39.mlp.gate_proj",
93
+ "53.mlp.gate_proj",
94
+ "43.mlp.up_proj",
95
+ "58.mlp.gate_proj",
96
+ "61.mlp.gate_proj",
97
+ "layers.10.mlp.up_proj",
98
+ "layers.18.mlp.up_proj",
99
+ "39.mlp.down_proj",
100
+ "53.mlp.down_proj",
101
+ "layers.20.mlp.gate_proj",
102
+ "v_proj",
103
+ "46.mlp.down_proj",
104
+ "38.mlp.down_proj",
105
+ "61.mlp.down_proj",
106
+ "layers.0.mlp.down_proj",
107
+ "layers.27.mlp.gate_proj",
108
+ "layers.9.mlp.up_proj",
109
+ "layers.5.mlp.gate_proj",
110
+ "62.mlp.down_proj",
111
+ "k_proj",
112
+ "layers.17.mlp.up_proj",
113
+ "47.mlp.gate_proj",
114
+ "48.mlp.gate_proj",
115
+ "layers.22.mlp.down_proj",
116
+ "layers.15.mlp.gate_proj",
117
+ "layers.16.mlp.up_proj",
118
+ "34.mlp.down_proj",
119
+ "layers.4.mlp.up_proj",
120
+ "layers.26.mlp.gate_proj",
121
+ "34.mlp.up_proj",
122
+ "53.mlp.up_proj",
123
+ "59.mlp.down_proj",
124
+ "layers.22.mlp.up_proj",
125
+ "38.mlp.gate_proj",
126
+ "50.mlp.gate_proj",
127
+ "layers.13.mlp.down_proj",
128
+ "layers.8.mlp.down_proj",
129
+ "layers.2.mlp.up_proj",
130
+ "layers.30.mlp.gate_proj",
131
+ "layers.17.mlp.gate_proj",
132
+ "50.mlp.up_proj",
133
+ "layers.30.mlp.down_proj",
134
+ "54.mlp.gate_proj",
135
+ "52.mlp.up_proj",
136
+ "layers.5.mlp.down_proj",
137
+ "layers.8.mlp.gate_proj",
138
+ "49.mlp.gate_proj",
139
+ "layers.28.mlp.gate_proj",
140
+ "35.mlp.up_proj",
141
+ "33.mlp.up_proj",
142
+ "layers.2.mlp.gate_proj",
143
+ "58.mlp.down_proj",
144
+ "layers.4.mlp.gate_proj",
145
+ "57.mlp.gate_proj",
146
+ "layers.28.mlp.up_proj",
147
+ "layers.29.mlp.gate_proj",
148
+ "51.mlp.gate_proj",
149
+ "layers.5.mlp.up_proj",
150
+ "51.mlp.down_proj",
151
+ "61.mlp.up_proj",
152
+ "44.mlp.gate_proj",
153
+ "35.mlp.down_proj",
154
+ "layers.2.mlp.down_proj",
155
+ "44.mlp.down_proj",
156
+ "layers.15.mlp.up_proj",
157
+ "layers.9.mlp.gate_proj",
158
+ "layers.14.mlp.up_proj",
159
+ "layers.23.mlp.up_proj",
160
+ "43.mlp.down_proj",
161
+ "o_proj",
162
+ "34.mlp.gate_proj",
163
+ "layers.29.mlp.up_proj",
164
+ "38.mlp.up_proj",
165
+ "54.mlp.down_proj",
166
+ "41.mlp.down_proj",
167
+ "layers.12.mlp.gate_proj",
168
+ "layers.20.mlp.up_proj",
169
+ "32.mlp.gate_proj",
170
+ "40.mlp.gate_proj",
171
+ "43.mlp.gate_proj",
172
+ "37.mlp.gate_proj",
173
+ "44.mlp.up_proj",
174
+ "layers.11.mlp.up_proj",
175
+ "layers.1.mlp.gate_proj",
176
+ "55.mlp.gate_proj",
177
+ "36.mlp.down_proj",
178
+ "layers.31.mlp.down_proj",
179
+ "layers.19.mlp.down_proj",
180
+ "63.mlp.gate_proj",
181
+ "layers.17.mlp.down_proj",
182
+ "layers.20.mlp.down_proj",
183
+ "layers.6.mlp.down_proj",
184
+ "layers.27.mlp.down_proj",
185
+ "56.mlp.up_proj",
186
+ "35.mlp.gate_proj",
187
+ "layers.12.mlp.up_proj",
188
+ "layers.13.mlp.up_proj",
189
+ "52.mlp.gate_proj",
190
+ "layers.24.mlp.up_proj",
191
+ "47.mlp.down_proj",
192
+ "layers.26.mlp.up_proj",
193
+ "layers.11.mlp.down_proj",
194
+ "layers.25.mlp.gate_proj",
195
+ "layers.26.mlp.down_proj",
196
+ "48.mlp.up_proj",
197
+ "layers.3.mlp.gate_proj",
198
+ "layers.31.mlp.up_proj",
199
+ "40.mlp.down_proj",
200
+ "layers.19.mlp.up_proj",
201
+ "layers.9.mlp.down_proj",
202
+ "63.mlp.up_proj",
203
+ "36.mlp.gate_proj",
204
+ "layers.23.mlp.gate_proj",
205
+ "layers.1.mlp.up_proj",
206
+ "42.mlp.gate_proj",
207
+ "layers.31.mlp.gate_proj",
208
+ "45.mlp.up_proj",
209
+ "layers.10.mlp.down_proj",
210
+ "layers.7.mlp.down_proj",
211
+ "layers.27.mlp.up_proj",
212
+ "57.mlp.up_proj",
213
+ "60.mlp.up_proj",
214
+ "46.mlp.up_proj",
215
+ "layers.21.mlp.down_proj",
216
+ "60.mlp.down_proj",
217
+ "layers.25.mlp.down_proj",
218
+ "layers.23.mlp.down_proj",
219
+ "layers.11.mlp.gate_proj",
220
+ "46.mlp.gate_proj",
221
+ "32.mlp.up_proj",
222
+ "59.mlp.up_proj"
223
+ ],
224
+ "task_type": "CAUSAL_LM",
225
+ "trainable_token_indices": null,
226
+ "use_dora": false,
227
+ "use_rslora": false
228
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecffef0f7e38b2dd6e8e13c9d79c95ed17862f02dc69ff0c810ed3899110fc42
3
+ size 268555264
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 4846754092548096.0,
4
+ "train_loss": 0.08037865161895752,
5
+ "train_runtime": 27.5144,
6
+ "train_samples_per_second": 0.327,
7
+ "train_steps_per_second": 0.109
8
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
checkpoint-3/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-VL-32B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.1
checkpoint-3/adapter_config.json ADDED
@@ -0,0 +1,228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-32B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "33.mlp.down_proj",
28
+ "59.mlp.gate_proj",
29
+ "layers.19.mlp.gate_proj",
30
+ "layers.6.mlp.up_proj",
31
+ "layers.21.mlp.up_proj",
32
+ "37.mlp.down_proj",
33
+ "52.mlp.down_proj",
34
+ "60.mlp.gate_proj",
35
+ "layers.3.mlp.up_proj",
36
+ "37.mlp.up_proj",
37
+ "47.mlp.up_proj",
38
+ "62.mlp.up_proj",
39
+ "layers.12.mlp.down_proj",
40
+ "50.mlp.down_proj",
41
+ "layers.3.mlp.down_proj",
42
+ "layers.7.mlp.up_proj",
43
+ "55.mlp.up_proj",
44
+ "57.mlp.down_proj",
45
+ "layers.14.mlp.down_proj",
46
+ "layers.24.mlp.down_proj",
47
+ "58.mlp.up_proj",
48
+ "layers.21.mlp.gate_proj",
49
+ "42.mlp.up_proj",
50
+ "layers.30.mlp.up_proj",
51
+ "layers.6.mlp.gate_proj",
52
+ "56.mlp.gate_proj",
53
+ "56.mlp.down_proj",
54
+ "49.mlp.up_proj",
55
+ "layers.29.mlp.down_proj",
56
+ "q_proj",
57
+ "55.mlp.down_proj",
58
+ "layers.14.mlp.gate_proj",
59
+ "layers.16.mlp.gate_proj",
60
+ "51.mlp.up_proj",
61
+ "layers.10.mlp.gate_proj",
62
+ "45.mlp.gate_proj",
63
+ "layers.25.mlp.up_proj",
64
+ "layers.13.mlp.gate_proj",
65
+ "layers.24.mlp.gate_proj",
66
+ "41.mlp.up_proj",
67
+ "45.mlp.down_proj",
68
+ "41.mlp.gate_proj",
69
+ "48.mlp.down_proj",
70
+ "layers.28.mlp.down_proj",
71
+ "layers.18.mlp.down_proj",
72
+ "33.mlp.gate_proj",
73
+ "36.mlp.up_proj",
74
+ "layers.1.mlp.down_proj",
75
+ "layers.0.mlp.gate_proj",
76
+ "63.mlp.down_proj",
77
+ "layers.15.mlp.down_proj",
78
+ "40.mlp.up_proj",
79
+ "layers.0.mlp.up_proj",
80
+ "layers.4.mlp.down_proj",
81
+ "32.mlp.down_proj",
82
+ "42.mlp.down_proj",
83
+ "layers.7.mlp.gate_proj",
84
+ "layers.22.mlp.gate_proj",
85
+ "layers.18.mlp.gate_proj",
86
+ "layers.8.mlp.up_proj",
87
+ "39.mlp.up_proj",
88
+ "layers.16.mlp.down_proj",
89
+ "49.mlp.down_proj",
90
+ "62.mlp.gate_proj",
91
+ "54.mlp.up_proj",
92
+ "39.mlp.gate_proj",
93
+ "53.mlp.gate_proj",
94
+ "43.mlp.up_proj",
95
+ "58.mlp.gate_proj",
96
+ "61.mlp.gate_proj",
97
+ "layers.10.mlp.up_proj",
98
+ "layers.18.mlp.up_proj",
99
+ "39.mlp.down_proj",
100
+ "53.mlp.down_proj",
101
+ "layers.20.mlp.gate_proj",
102
+ "v_proj",
103
+ "46.mlp.down_proj",
104
+ "38.mlp.down_proj",
105
+ "61.mlp.down_proj",
106
+ "layers.0.mlp.down_proj",
107
+ "layers.27.mlp.gate_proj",
108
+ "layers.9.mlp.up_proj",
109
+ "layers.5.mlp.gate_proj",
110
+ "62.mlp.down_proj",
111
+ "k_proj",
112
+ "layers.17.mlp.up_proj",
113
+ "47.mlp.gate_proj",
114
+ "48.mlp.gate_proj",
115
+ "layers.22.mlp.down_proj",
116
+ "layers.15.mlp.gate_proj",
117
+ "layers.16.mlp.up_proj",
118
+ "34.mlp.down_proj",
119
+ "layers.4.mlp.up_proj",
120
+ "layers.26.mlp.gate_proj",
121
+ "34.mlp.up_proj",
122
+ "53.mlp.up_proj",
123
+ "59.mlp.down_proj",
124
+ "layers.22.mlp.up_proj",
125
+ "38.mlp.gate_proj",
126
+ "50.mlp.gate_proj",
127
+ "layers.13.mlp.down_proj",
128
+ "layers.8.mlp.down_proj",
129
+ "layers.2.mlp.up_proj",
130
+ "layers.30.mlp.gate_proj",
131
+ "layers.17.mlp.gate_proj",
132
+ "50.mlp.up_proj",
133
+ "layers.30.mlp.down_proj",
134
+ "54.mlp.gate_proj",
135
+ "52.mlp.up_proj",
136
+ "layers.5.mlp.down_proj",
137
+ "layers.8.mlp.gate_proj",
138
+ "49.mlp.gate_proj",
139
+ "layers.28.mlp.gate_proj",
140
+ "35.mlp.up_proj",
141
+ "33.mlp.up_proj",
142
+ "layers.2.mlp.gate_proj",
143
+ "58.mlp.down_proj",
144
+ "layers.4.mlp.gate_proj",
145
+ "57.mlp.gate_proj",
146
+ "layers.28.mlp.up_proj",
147
+ "layers.29.mlp.gate_proj",
148
+ "51.mlp.gate_proj",
149
+ "layers.5.mlp.up_proj",
150
+ "51.mlp.down_proj",
151
+ "61.mlp.up_proj",
152
+ "44.mlp.gate_proj",
153
+ "35.mlp.down_proj",
154
+ "layers.2.mlp.down_proj",
155
+ "44.mlp.down_proj",
156
+ "layers.15.mlp.up_proj",
157
+ "layers.9.mlp.gate_proj",
158
+ "layers.14.mlp.up_proj",
159
+ "layers.23.mlp.up_proj",
160
+ "43.mlp.down_proj",
161
+ "o_proj",
162
+ "34.mlp.gate_proj",
163
+ "layers.29.mlp.up_proj",
164
+ "38.mlp.up_proj",
165
+ "54.mlp.down_proj",
166
+ "41.mlp.down_proj",
167
+ "layers.12.mlp.gate_proj",
168
+ "layers.20.mlp.up_proj",
169
+ "32.mlp.gate_proj",
170
+ "40.mlp.gate_proj",
171
+ "43.mlp.gate_proj",
172
+ "37.mlp.gate_proj",
173
+ "44.mlp.up_proj",
174
+ "layers.11.mlp.up_proj",
175
+ "layers.1.mlp.gate_proj",
176
+ "55.mlp.gate_proj",
177
+ "36.mlp.down_proj",
178
+ "layers.31.mlp.down_proj",
179
+ "layers.19.mlp.down_proj",
180
+ "63.mlp.gate_proj",
181
+ "layers.17.mlp.down_proj",
182
+ "layers.20.mlp.down_proj",
183
+ "layers.6.mlp.down_proj",
184
+ "layers.27.mlp.down_proj",
185
+ "56.mlp.up_proj",
186
+ "35.mlp.gate_proj",
187
+ "layers.12.mlp.up_proj",
188
+ "layers.13.mlp.up_proj",
189
+ "52.mlp.gate_proj",
190
+ "layers.24.mlp.up_proj",
191
+ "47.mlp.down_proj",
192
+ "layers.26.mlp.up_proj",
193
+ "layers.11.mlp.down_proj",
194
+ "layers.25.mlp.gate_proj",
195
+ "layers.26.mlp.down_proj",
196
+ "48.mlp.up_proj",
197
+ "layers.3.mlp.gate_proj",
198
+ "layers.31.mlp.up_proj",
199
+ "40.mlp.down_proj",
200
+ "layers.19.mlp.up_proj",
201
+ "layers.9.mlp.down_proj",
202
+ "63.mlp.up_proj",
203
+ "36.mlp.gate_proj",
204
+ "layers.23.mlp.gate_proj",
205
+ "layers.1.mlp.up_proj",
206
+ "42.mlp.gate_proj",
207
+ "layers.31.mlp.gate_proj",
208
+ "45.mlp.up_proj",
209
+ "layers.10.mlp.down_proj",
210
+ "layers.7.mlp.down_proj",
211
+ "layers.27.mlp.up_proj",
212
+ "57.mlp.up_proj",
213
+ "60.mlp.up_proj",
214
+ "46.mlp.up_proj",
215
+ "layers.21.mlp.down_proj",
216
+ "60.mlp.down_proj",
217
+ "layers.25.mlp.down_proj",
218
+ "layers.23.mlp.down_proj",
219
+ "layers.11.mlp.gate_proj",
220
+ "46.mlp.gate_proj",
221
+ "32.mlp.up_proj",
222
+ "59.mlp.up_proj"
223
+ ],
224
+ "task_type": "CAUSAL_LM",
225
+ "trainable_token_indices": null,
226
+ "use_dora": false,
227
+ "use_rslora": false
228
+ }
checkpoint-3/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecffef0f7e38b2dd6e8e13c9d79c95ed17862f02dc69ff0c810ed3899110fc42
3
+ size 268555264
checkpoint-3/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-3/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
checkpoint-3/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201d98ea0ea7d2e54c5cc55635bc79eab5fb5ec65de5d8545a969d26d6e0d5ac
3
+ size 537626770
checkpoint-3/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
checkpoint-3/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
3
+ size 14512
checkpoint-3/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
3
+ size 14512
checkpoint-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bace611bec546b6196769d18099d0892bded57db054c98eceb3962aefa06a10
3
+ size 1064
checkpoint-3/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-3/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-3/tokenizer_config.json ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "processor_class": "Qwen2_5_VLProcessor",
207
+ "split_special_tokens": false,
208
+ "tokenizer_class": "Qwen2Tokenizer",
209
+ "unk_token": null
210
+ }
checkpoint-3/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 10,
13
+ "max_steps": 3,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 3,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 4846754092548096.0,
30
+ "train_batch_size": 2,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2891fd07d7afd4d7d2e595e05f254422e9bbf55e5b8ba96580f9543bdd2651f
3
+ size 5752
checkpoint-3/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "processor_class": "Qwen2_5_VLProcessor",
207
+ "split_special_tokens": false,
208
+ "tokenizer_class": "Qwen2Tokenizer",
209
+ "unk_token": null
210
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 4846754092548096.0,
4
+ "train_loss": 0.08037865161895752,
5
+ "train_runtime": 27.5144,
6
+ "train_samples_per_second": 0.327,
7
+ "train_steps_per_second": 0.109
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"current_steps": 3, "total_steps": 3, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:00:25", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 3.0,
14
+ "step": 3,
15
+ "total_flos": 4846754092548096.0,
16
+ "train_loss": 0.08037865161895752,
17
+ "train_runtime": 27.5144,
18
+ "train_samples_per_second": 0.327,
19
+ "train_steps_per_second": 0.109
20
+ }
21
+ ],
22
+ "logging_steps": 10,
23
+ "max_steps": 3,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 3,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": true
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 4846754092548096.0,
40
+ "train_batch_size": 2,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2891fd07d7afd4d7d2e595e05f254422e9bbf55e5b8ba96580f9543bdd2651f
3
+ size 5752
vocab.json ADDED
The diff for this file is too large to render. See raw diff