Hugging Face's logo

Ba2han
/
augment5-4b-fp8-GPTQ

Image-Text-to-Text
Transformers
Safetensors
gemma3
conversational
text-generation-inference
compressed-tensors
Model card Files
xet
 Community
Ba2han commited on
Commit
fd7ff67
·
verified ·
1 Parent(s): a614ee5

Upload Gemma3ForConditionalGeneration

Browse files
Files changed (6) hide show
  1. README.md +199 -0
  2. config.json +306 -0
  3. generation_config.json +7 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +0 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
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
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
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]
config.json ADDED
@@ -0,0 +1,306 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "dtype": "float16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 106,
10
+ "image_token_index": 262144,
11
+ "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_type": "gemma3",
14
+ "pad_token_id": 0,
15
+ "quantization_config": {
16
+ "config_groups": {
17
+ "group_0": {
18
+ "format": "float-quantized",
19
+ "input_activations": {
20
+ "actorder": null,
21
+ "block_structure": null,
22
+ "dynamic": true,
23
+ "group_size": null,
24
+ "num_bits": 8,
25
+ "observer": null,
26
+ "observer_kwargs": {},
27
+ "strategy": "token",
28
+ "symmetric": true,
29
+ "type": "float"
30
+ },
31
+ "output_activations": null,
32
+ "targets": [
33
+ "Linear"
34
+ ],
35
+ "weights": {
36
+ "actorder": null,
37
+ "block_structure": null,
38
+ "dynamic": false,
39
+ "group_size": null,
40
+ "num_bits": 8,
41
+ "observer": "minmax",
42
+ "observer_kwargs": {},
43
+ "strategy": "channel",
44
+ "symmetric": true,
45
+ "type": "float"
46
+ }
47
+ }
48
+ },
49
+ "format": "float-quantized",
50
+ "global_compression_ratio": null,
51
+ "ignore": [
52
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
53
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
54
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
55
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
56
+ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1",
57
+ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2",
58
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
59
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
60
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
61
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
62
+ "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1",
63
+ "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2",
64
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
65
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
66
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
67
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
68
+ "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1",
69
+ "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2",
70
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
71
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
72
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
73
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
74
+ "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1",
75
+ "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2",
76
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
77
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
78
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
79
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
80
+ "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1",
81
+ "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2",
82
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
83
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
84
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
85
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
86
+ "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1",
87
+ "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2",
88
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
89
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
90
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
91
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
92
+ "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1",
93
+ "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2",
94
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
95
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
96
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
97
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
98
+ "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1",
99
+ "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2",
100
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
101
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
102
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
103
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
104
+ "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1",
105
+ "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2",
106
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
107
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
108
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
109
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
110
+ "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1",
111
+ "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2",
112
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
113
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
114
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
115
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
116
+ "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1",
117
+ "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2",
118
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
119
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
120
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
121
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
122
+ "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1",
123
+ "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2",
124
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
125
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
126
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
127
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
128
+ "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1",
129
+ "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2",
130
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
131
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
132
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
133
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
134
+ "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1",
135
+ "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2",
136
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
137
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
138
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
139
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
140
+ "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1",
141
+ "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2",
142
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
143
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
144
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
145
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
146
+ "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1",
147
+ "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2",
148
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
149
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
150
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
151
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
152
+ "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1",
153
+ "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2",
154
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
155
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
156
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
157
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
158
+ "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1",
159
+ "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2",
160
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
161
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
162
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
163
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
164
+ "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1",
165
+ "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2",
166
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
167
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
168
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
169
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
170
+ "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1",
171
+ "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2",
172
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
173
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
174
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
175
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
176
+ "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1",
177
+ "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2",
178
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
179
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
180
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
181
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
182
+ "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1",
183
+ "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2",
184
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
185
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
186
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
187
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
188
+ "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1",
189
+ "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2",
190
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
191
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
192
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
193
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
194
+ "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1",
195
+ "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2",
196
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj",
197
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj",
198
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj",
199
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj",
200
+ "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1",
201
+ "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2",
202
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj",
203
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj",
204
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj",
205
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj",
206
+ "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1",
207
+ "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2",
208
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj",
209
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj",
210
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj",
211
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj",
212
+ "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1",
213
+ "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2",
214
+ "lm_head"
215
+ ],
216
+ "kv_cache_scheme": null,
217
+ "quant_method": "compressed-tensors",
218
+ "quantization_status": "compressed",
219
+ "sparsity_config": {}
220
+ },
221
+ "text_config": {
222
+ "_sliding_window_pattern": 6,
223
+ "attention_bias": false,
224
+ "attention_dropout": 0.0,
225
+ "attn_logit_softcapping": null,
226
+ "cache_implementation": "hybrid",
227
+ "dtype": "float16",
228
+ "final_logit_softcapping": null,
229
+ "head_dim": 256,
230
+ "hidden_activation": "gelu_pytorch_tanh",
231
+ "hidden_size": 2560,
232
+ "initializer_range": 0.02,
233
+ "intermediate_size": 10240,
234
+ "layer_types": [
235
+ "sliding_attention",
236
+ "sliding_attention",
237
+ "sliding_attention",
238
+ "sliding_attention",
239
+ "sliding_attention",
240
+ "full_attention",
241
+ "sliding_attention",
242
+ "sliding_attention",
243
+ "sliding_attention",
244
+ "sliding_attention",
245
+ "sliding_attention",
246
+ "full_attention",
247
+ "sliding_attention",
248
+ "sliding_attention",
249
+ "sliding_attention",
250
+ "sliding_attention",
251
+ "sliding_attention",
252
+ "full_attention",
253
+ "sliding_attention",
254
+ "sliding_attention",
255
+ "sliding_attention",
256
+ "sliding_attention",
257
+ "sliding_attention",
258
+ "full_attention",
259
+ "sliding_attention",
260
+ "sliding_attention",
261
+ "sliding_attention",
262
+ "sliding_attention",
263
+ "sliding_attention",
264
+ "full_attention",
265
+ "sliding_attention",
266
+ "sliding_attention",
267
+ "sliding_attention",
268
+ "sliding_attention"
269
+ ],
270
+ "max_position_embeddings": 131072,
271
+ "model_type": "gemma3_text",
272
+ "num_attention_heads": 8,
273
+ "num_hidden_layers": 34,
274
+ "num_key_value_heads": 4,
275
+ "query_pre_attn_scalar": 256,
276
+ "rms_norm_eps": 1e-06,
277
+ "rope_local_base_freq": 10000.0,
278
+ "rope_scaling": {
279
+ "factor": 8.0,
280
+ "rope_type": "linear"
281
+ },
282
+ "rope_theta": 1000000.0,
283
+ "sliding_window": 1024,
284
+ "use_cache": true,
285
+ "vocab_size": 262208
286
+ },
287
+ "tie_word_embeddings": false,
288
+ "transformers_version": "4.56.2",
289
+ "unsloth_fixed": true,
290
+ "unsloth_version": "2025.10.1",
291
+ "vision_config": {
292
+ "attention_dropout": 0.0,
293
+ "dtype": "float16",
294
+ "hidden_act": "gelu_pytorch_tanh",
295
+ "hidden_size": 1152,
296
+ "image_size": 896,
297
+ "intermediate_size": 4304,
298
+ "layer_norm_eps": 1e-06,
299
+ "model_type": "siglip_vision_model",
300
+ "num_attention_heads": 16,
301
+ "num_channels": 3,
302
+ "num_hidden_layers": 27,
303
+ "patch_size": 14,
304
+ "vision_use_head": false
305
+ }
306
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 106,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.56.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc1b007d47db4c65a0dd94695309680acbce4815ab234ad09f60522b296519c
3
+ size 4962155976
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f5fa4745bb52dba6010465096c34170990055fd189a928f3384c81b4af2b92
3
+ size 3640172040
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff