Hugging Face's logo

Ba2han
/
Mistral-Geminized-w8a8

Image-Text-to-Text
Transformers
Safetensors
mistral3
conversational
compressed-tensors
Model card Files
xet
 Community
Ba2han commited on
Commit
6bb39e9
·
verified ·
1 Parent(s): b78b061

Upload Mistral3ForConditionalGeneration

Browse files
Files changed (11) hide show
  1. README.md +199 -0
  2. config.json +281 -0
  3. generation_config.json +11 -0
  4. model-00001-of-00006.safetensors +3 -0
  5. model-00002-of-00006.safetensors +3 -0
  6. model-00003-of-00006.safetensors +3 -0
  7. model-00004-of-00006.safetensors +3 -0
  8. model-00005-of-00006.safetensors +3 -0
  9. model-00006-of-00006.safetensors +3 -0
  10. model.safetensors.index.json +0 -0
  11. recipe.yaml +43 -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 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Mistral3ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 2,
8
+ "image_token_index": 10,
9
+ "model_type": "mistral3",
10
+ "multimodal_projector_bias": false,
11
+ "pad_token_id": 11,
12
+ "projector_hidden_act": "gelu",
13
+ "quantization_config": {
14
+ "config_groups": {
15
+ "group_0": {
16
+ "format": "float-quantized",
17
+ "input_activations": {
18
+ "actorder": null,
19
+ "block_structure": null,
20
+ "dynamic": false,
21
+ "group_size": null,
22
+ "num_bits": 8,
23
+ "observer": "minmax",
24
+ "observer_kwargs": {},
25
+ "strategy": "tensor",
26
+ "symmetric": true,
27
+ "type": "float"
28
+ },
29
+ "output_activations": null,
30
+ "targets": [
31
+ "Linear"
32
+ ],
33
+ "weights": {
34
+ "actorder": null,
35
+ "block_structure": null,
36
+ "dynamic": false,
37
+ "group_size": null,
38
+ "num_bits": 8,
39
+ "observer": "minmax",
40
+ "observer_kwargs": {},
41
+ "strategy": "tensor",
42
+ "symmetric": true,
43
+ "type": "float"
44
+ }
45
+ }
46
+ },
47
+ "format": "float-quantized",
48
+ "global_compression_ratio": null,
49
+ "ignore": [
50
+ "model.vision_tower.transformer.layers.0.feed_forward.gate_proj",
51
+ "model.vision_tower.transformer.layers.0.feed_forward.up_proj",
52
+ "model.vision_tower.transformer.layers.0.feed_forward.down_proj",
53
+ "model.vision_tower.transformer.layers.0.attention.k_proj",
54
+ "model.vision_tower.transformer.layers.0.attention.v_proj",
55
+ "model.vision_tower.transformer.layers.0.attention.q_proj",
56
+ "model.vision_tower.transformer.layers.0.attention.o_proj",
57
+ "model.vision_tower.transformer.layers.1.feed_forward.gate_proj",
58
+ "model.vision_tower.transformer.layers.1.feed_forward.up_proj",
59
+ "model.vision_tower.transformer.layers.1.feed_forward.down_proj",
60
+ "model.vision_tower.transformer.layers.1.attention.k_proj",
61
+ "model.vision_tower.transformer.layers.1.attention.v_proj",
62
+ "model.vision_tower.transformer.layers.1.attention.q_proj",
63
+ "model.vision_tower.transformer.layers.1.attention.o_proj",
64
+ "model.vision_tower.transformer.layers.2.feed_forward.gate_proj",
65
+ "model.vision_tower.transformer.layers.2.feed_forward.up_proj",
66
+ "model.vision_tower.transformer.layers.2.feed_forward.down_proj",
67
+ "model.vision_tower.transformer.layers.2.attention.k_proj",
68
+ "model.vision_tower.transformer.layers.2.attention.v_proj",
69
+ "model.vision_tower.transformer.layers.2.attention.q_proj",
70
+ "model.vision_tower.transformer.layers.2.attention.o_proj",
71
+ "model.vision_tower.transformer.layers.3.feed_forward.gate_proj",
72
+ "model.vision_tower.transformer.layers.3.feed_forward.up_proj",
73
+ "model.vision_tower.transformer.layers.3.feed_forward.down_proj",
74
+ "model.vision_tower.transformer.layers.3.attention.k_proj",
75
+ "model.vision_tower.transformer.layers.3.attention.v_proj",
76
+ "model.vision_tower.transformer.layers.3.attention.q_proj",
77
+ "model.vision_tower.transformer.layers.3.attention.o_proj",
78
+ "model.vision_tower.transformer.layers.4.feed_forward.gate_proj",
79
+ "model.vision_tower.transformer.layers.4.feed_forward.up_proj",
80
+ "model.vision_tower.transformer.layers.4.feed_forward.down_proj",
81
+ "model.vision_tower.transformer.layers.4.attention.k_proj",
82
+ "model.vision_tower.transformer.layers.4.attention.v_proj",
83
+ "model.vision_tower.transformer.layers.4.attention.q_proj",
84
+ "model.vision_tower.transformer.layers.4.attention.o_proj",
85
+ "model.vision_tower.transformer.layers.5.feed_forward.gate_proj",
86
+ "model.vision_tower.transformer.layers.5.feed_forward.up_proj",
87
+ "model.vision_tower.transformer.layers.5.feed_forward.down_proj",
88
+ "model.vision_tower.transformer.layers.5.attention.k_proj",
89
+ "model.vision_tower.transformer.layers.5.attention.v_proj",
90
+ "model.vision_tower.transformer.layers.5.attention.q_proj",
91
+ "model.vision_tower.transformer.layers.5.attention.o_proj",
92
+ "model.vision_tower.transformer.layers.6.feed_forward.gate_proj",
93
+ "model.vision_tower.transformer.layers.6.feed_forward.up_proj",
94
+ "model.vision_tower.transformer.layers.6.feed_forward.down_proj",
95
+ "model.vision_tower.transformer.layers.6.attention.k_proj",
96
+ "model.vision_tower.transformer.layers.6.attention.v_proj",
97
+ "model.vision_tower.transformer.layers.6.attention.q_proj",
98
+ "model.vision_tower.transformer.layers.6.attention.o_proj",
99
+ "model.vision_tower.transformer.layers.7.feed_forward.gate_proj",
100
+ "model.vision_tower.transformer.layers.7.feed_forward.up_proj",
101
+ "model.vision_tower.transformer.layers.7.feed_forward.down_proj",
102
+ "model.vision_tower.transformer.layers.7.attention.k_proj",
103
+ "model.vision_tower.transformer.layers.7.attention.v_proj",
104
+ "model.vision_tower.transformer.layers.7.attention.q_proj",
105
+ "model.vision_tower.transformer.layers.7.attention.o_proj",
106
+ "model.vision_tower.transformer.layers.8.feed_forward.gate_proj",
107
+ "model.vision_tower.transformer.layers.8.feed_forward.up_proj",
108
+ "model.vision_tower.transformer.layers.8.feed_forward.down_proj",
109
+ "model.vision_tower.transformer.layers.8.attention.k_proj",
110
+ "model.vision_tower.transformer.layers.8.attention.v_proj",
111
+ "model.vision_tower.transformer.layers.8.attention.q_proj",
112
+ "model.vision_tower.transformer.layers.8.attention.o_proj",
113
+ "model.vision_tower.transformer.layers.9.feed_forward.gate_proj",
114
+ "model.vision_tower.transformer.layers.9.feed_forward.up_proj",
115
+ "model.vision_tower.transformer.layers.9.feed_forward.down_proj",
116
+ "model.vision_tower.transformer.layers.9.attention.k_proj",
117
+ "model.vision_tower.transformer.layers.9.attention.v_proj",
118
+ "model.vision_tower.transformer.layers.9.attention.q_proj",
119
+ "model.vision_tower.transformer.layers.9.attention.o_proj",
120
+ "model.vision_tower.transformer.layers.10.feed_forward.gate_proj",
121
+ "model.vision_tower.transformer.layers.10.feed_forward.up_proj",
122
+ "model.vision_tower.transformer.layers.10.feed_forward.down_proj",
123
+ "model.vision_tower.transformer.layers.10.attention.k_proj",
124
+ "model.vision_tower.transformer.layers.10.attention.v_proj",
125
+ "model.vision_tower.transformer.layers.10.attention.q_proj",
126
+ "model.vision_tower.transformer.layers.10.attention.o_proj",
127
+ "model.vision_tower.transformer.layers.11.feed_forward.gate_proj",
128
+ "model.vision_tower.transformer.layers.11.feed_forward.up_proj",
129
+ "model.vision_tower.transformer.layers.11.feed_forward.down_proj",
130
+ "model.vision_tower.transformer.layers.11.attention.k_proj",
131
+ "model.vision_tower.transformer.layers.11.attention.v_proj",
132
+ "model.vision_tower.transformer.layers.11.attention.q_proj",
133
+ "model.vision_tower.transformer.layers.11.attention.o_proj",
134
+ "model.vision_tower.transformer.layers.12.feed_forward.gate_proj",
135
+ "model.vision_tower.transformer.layers.12.feed_forward.up_proj",
136
+ "model.vision_tower.transformer.layers.12.feed_forward.down_proj",
137
+ "model.vision_tower.transformer.layers.12.attention.k_proj",
138
+ "model.vision_tower.transformer.layers.12.attention.v_proj",
139
+ "model.vision_tower.transformer.layers.12.attention.q_proj",
140
+ "model.vision_tower.transformer.layers.12.attention.o_proj",
141
+ "model.vision_tower.transformer.layers.13.feed_forward.gate_proj",
142
+ "model.vision_tower.transformer.layers.13.feed_forward.up_proj",
143
+ "model.vision_tower.transformer.layers.13.feed_forward.down_proj",
144
+ "model.vision_tower.transformer.layers.13.attention.k_proj",
145
+ "model.vision_tower.transformer.layers.13.attention.v_proj",
146
+ "model.vision_tower.transformer.layers.13.attention.q_proj",
147
+ "model.vision_tower.transformer.layers.13.attention.o_proj",
148
+ "model.vision_tower.transformer.layers.14.feed_forward.gate_proj",
149
+ "model.vision_tower.transformer.layers.14.feed_forward.up_proj",
150
+ "model.vision_tower.transformer.layers.14.feed_forward.down_proj",
151
+ "model.vision_tower.transformer.layers.14.attention.k_proj",
152
+ "model.vision_tower.transformer.layers.14.attention.v_proj",
153
+ "model.vision_tower.transformer.layers.14.attention.q_proj",
154
+ "model.vision_tower.transformer.layers.14.attention.o_proj",
155
+ "model.vision_tower.transformer.layers.15.feed_forward.gate_proj",
156
+ "model.vision_tower.transformer.layers.15.feed_forward.up_proj",
157
+ "model.vision_tower.transformer.layers.15.feed_forward.down_proj",
158
+ "model.vision_tower.transformer.layers.15.attention.k_proj",
159
+ "model.vision_tower.transformer.layers.15.attention.v_proj",
160
+ "model.vision_tower.transformer.layers.15.attention.q_proj",
161
+ "model.vision_tower.transformer.layers.15.attention.o_proj",
162
+ "model.vision_tower.transformer.layers.16.feed_forward.gate_proj",
163
+ "model.vision_tower.transformer.layers.16.feed_forward.up_proj",
164
+ "model.vision_tower.transformer.layers.16.feed_forward.down_proj",
165
+ "model.vision_tower.transformer.layers.16.attention.k_proj",
166
+ "model.vision_tower.transformer.layers.16.attention.v_proj",
167
+ "model.vision_tower.transformer.layers.16.attention.q_proj",
168
+ "model.vision_tower.transformer.layers.16.attention.o_proj",
169
+ "model.vision_tower.transformer.layers.17.feed_forward.gate_proj",
170
+ "model.vision_tower.transformer.layers.17.feed_forward.up_proj",
171
+ "model.vision_tower.transformer.layers.17.feed_forward.down_proj",
172
+ "model.vision_tower.transformer.layers.17.attention.k_proj",
173
+ "model.vision_tower.transformer.layers.17.attention.v_proj",
174
+ "model.vision_tower.transformer.layers.17.attention.q_proj",
175
+ "model.vision_tower.transformer.layers.17.attention.o_proj",
176
+ "model.vision_tower.transformer.layers.18.feed_forward.gate_proj",
177
+ "model.vision_tower.transformer.layers.18.feed_forward.up_proj",
178
+ "model.vision_tower.transformer.layers.18.feed_forward.down_proj",
179
+ "model.vision_tower.transformer.layers.18.attention.k_proj",
180
+ "model.vision_tower.transformer.layers.18.attention.v_proj",
181
+ "model.vision_tower.transformer.layers.18.attention.q_proj",
182
+ "model.vision_tower.transformer.layers.18.attention.o_proj",
183
+ "model.vision_tower.transformer.layers.19.feed_forward.gate_proj",
184
+ "model.vision_tower.transformer.layers.19.feed_forward.up_proj",
185
+ "model.vision_tower.transformer.layers.19.feed_forward.down_proj",
186
+ "model.vision_tower.transformer.layers.19.attention.k_proj",
187
+ "model.vision_tower.transformer.layers.19.attention.v_proj",
188
+ "model.vision_tower.transformer.layers.19.attention.q_proj",
189
+ "model.vision_tower.transformer.layers.19.attention.o_proj",
190
+ "model.vision_tower.transformer.layers.20.feed_forward.gate_proj",
191
+ "model.vision_tower.transformer.layers.20.feed_forward.up_proj",
192
+ "model.vision_tower.transformer.layers.20.feed_forward.down_proj",
193
+ "model.vision_tower.transformer.layers.20.attention.k_proj",
194
+ "model.vision_tower.transformer.layers.20.attention.v_proj",
195
+ "model.vision_tower.transformer.layers.20.attention.q_proj",
196
+ "model.vision_tower.transformer.layers.20.attention.o_proj",
197
+ "model.vision_tower.transformer.layers.21.feed_forward.gate_proj",
198
+ "model.vision_tower.transformer.layers.21.feed_forward.up_proj",
199
+ "model.vision_tower.transformer.layers.21.feed_forward.down_proj",
200
+ "model.vision_tower.transformer.layers.21.attention.k_proj",
201
+ "model.vision_tower.transformer.layers.21.attention.v_proj",
202
+ "model.vision_tower.transformer.layers.21.attention.q_proj",
203
+ "model.vision_tower.transformer.layers.21.attention.o_proj",
204
+ "model.vision_tower.transformer.layers.22.feed_forward.gate_proj",
205
+ "model.vision_tower.transformer.layers.22.feed_forward.up_proj",
206
+ "model.vision_tower.transformer.layers.22.feed_forward.down_proj",
207
+ "model.vision_tower.transformer.layers.22.attention.k_proj",
208
+ "model.vision_tower.transformer.layers.22.attention.v_proj",
209
+ "model.vision_tower.transformer.layers.22.attention.q_proj",
210
+ "model.vision_tower.transformer.layers.22.attention.o_proj",
211
+ "model.vision_tower.transformer.layers.23.feed_forward.gate_proj",
212
+ "model.vision_tower.transformer.layers.23.feed_forward.up_proj",
213
+ "model.vision_tower.transformer.layers.23.feed_forward.down_proj",
214
+ "model.vision_tower.transformer.layers.23.attention.k_proj",
215
+ "model.vision_tower.transformer.layers.23.attention.v_proj",
216
+ "model.vision_tower.transformer.layers.23.attention.q_proj",
217
+ "model.vision_tower.transformer.layers.23.attention.o_proj",
218
+ "model.multi_modal_projector.patch_merger.merging_layer",
219
+ "model.multi_modal_projector.linear_1",
220
+ "model.multi_modal_projector.linear_2",
221
+ "lm_head"
222
+ ],
223
+ "kv_cache_scheme": {
224
+ "actorder": null,
225
+ "block_structure": null,
226
+ "dynamic": false,
227
+ "group_size": null,
228
+ "num_bits": 8,
229
+ "observer": "minmax",
230
+ "observer_kwargs": {},
231
+ "strategy": "tensor",
232
+ "symmetric": true,
233
+ "type": "float"
234
+ },
235
+ "quant_method": "compressed-tensors",
236
+ "quantization_status": "compressed",
237
+ "sparsity_config": {},
238
+ "transform_config": {},
239
+ "version": "0.11.1.a20250918"
240
+ },
241
+ "spatial_merge_size": 2,
242
+ "text_config": {
243
+ "attention_dropout": 0.0,
244
+ "dtype": "bfloat16",
245
+ "head_dim": 128,
246
+ "hidden_act": "silu",
247
+ "hidden_size": 5120,
248
+ "initializer_range": 0.02,
249
+ "intermediate_size": 32768,
250
+ "max_position_embeddings": 131072,
251
+ "model_type": "mistral",
252
+ "num_attention_heads": 32,
253
+ "num_hidden_layers": 40,
254
+ "num_key_value_heads": 8,
255
+ "rms_norm_eps": 1e-05,
256
+ "rope_theta": 1000000000.0,
257
+ "sliding_window": null,
258
+ "use_cache": true,
259
+ "vocab_size": 131072
260
+ },
261
+ "tie_word_embeddings": false,
262
+ "transformers_version": "4.56.2",
263
+ "unsloth_fixed": true,
264
+ "vision_config": {
265
+ "attention_dropout": 0.0,
266
+ "dtype": "bfloat16",
267
+ "head_dim": 64,
268
+ "hidden_act": "silu",
269
+ "hidden_size": 1024,
270
+ "image_size": 1540,
271
+ "initializer_range": 0.02,
272
+ "intermediate_size": 4096,
273
+ "model_type": "pixtral",
274
+ "num_attention_heads": 16,
275
+ "num_channels": 3,
276
+ "num_hidden_layers": 24,
277
+ "patch_size": 14,
278
+ "rope_theta": 10000.0
279
+ },
280
+ "vision_feature_layer": -1
281
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_new_tokens": 131072,
7
+ "pad_token_id": 11,
8
+ "temperature": 0.7,
9
+ "top_p": 0.95,
10
+ "transformers_version": "4.56.2"
11
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7880bf9ca0992db96713063973b069a99c6a2a0d7cd2c0e9be086e55a03a0afe
3
+ size 4998969012
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec52bd1934f4d2ee288cf2cfa7c81ce37bbbcd8b321b9b4ee0870f35af3b5f0
3
+ size 4834126304
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052ce1c11d219a033d02faf561cacf8372114c1b67c28df47b36e17108b4b4f1
3
+ size 4834147436
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d725c69252fb7c347cc97c4eeab96f219eca91234eb563fa3f7834f0a7463790
3
+ size 4834147428
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd17010c3d86e8bce9a958675d55c7267322a55406c109ecd84ee2a41446faa2
3
+ size 4949499740
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487158e25eb90313f1f57a1894a260addf66dd6526984393fe8150abbe3c7a22
3
+ size 1342177424
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ quant_stage:
2
+ quant_modifiers:
3
+ QuantizationModifier:
4
+ config_groups:
5
+ group_0:
6
+ targets: [Linear]
7
+ weights:
8
+ num_bits: 8
9
+ type: float
10
+ symmetric: true
11
+ group_size: null
12
+ strategy: tensor
13
+ block_structure: null
14
+ dynamic: false
15
+ actorder: null
16
+ observer: minmax
17
+ observer_kwargs: {}
18
+ input_activations:
19
+ num_bits: 8
20
+ type: float
21
+ symmetric: true
22
+ group_size: null
23
+ strategy: tensor
24
+ block_structure: null
25
+ dynamic: false
26
+ actorder: null
27
+ observer: minmax
28
+ observer_kwargs: {}
29
+ output_activations: null
30
+ format: null
31
+ targets: [Linear]
32
+ ignore: [lm_head, 're:model\.vision_tower.*', 're:model\.multi_modal_projector.*']
33
+ kv_cache_scheme:
34
+ num_bits: 8
35
+ type: float
36
+ symmetric: true
37
+ group_size: null
38
+ strategy: tensor
39
+ block_structure: null
40
+ dynamic: false
41
+ actorder: null
42
+ observer: minmax
43
+ observer_kwargs: {}