Hugging Face's logo

hugging-quants
/
Llama-4-Scout-17B-16E-Instruct-fbgemm-unfused

Image-Text-to-Text
Transformers
Safetensors
llama4
conversational
text-generation-inference
fbgemm_fp8
Model card Files
xet
Community
medmekk HF Staff commited on
Commit
bed95f1
·
verified ·
1 Parent(s): 0471533

Upload Llama4ForConditionalGeneration

Browse files
Files changed (27) hide show
  1. README.md +199 -0
  2. config.json +609 -0
  3. generation_config.json +13 -0
  4. model-00001-of-00023.safetensors +3 -0
  5. model-00002-of-00023.safetensors +3 -0
  6. model-00003-of-00023.safetensors +3 -0
  7. model-00004-of-00023.safetensors +3 -0
  8. model-00005-of-00023.safetensors +3 -0
  9. model-00006-of-00023.safetensors +3 -0
  10. model-00007-of-00023.safetensors +3 -0
  11. model-00008-of-00023.safetensors +3 -0
  12. model-00009-of-00023.safetensors +3 -0
  13. model-00010-of-00023.safetensors +3 -0
  14. model-00011-of-00023.safetensors +3 -0
  15. model-00012-of-00023.safetensors +3 -0
  16. model-00013-of-00023.safetensors +3 -0
  17. model-00014-of-00023.safetensors +3 -0
  18. model-00015-of-00023.safetensors +3 -0
  19. model-00016-of-00023.safetensors +3 -0
  20. model-00017-of-00023.safetensors +3 -0
  21. model-00018-of-00023.safetensors +3 -0
  22. model-00019-of-00023.safetensors +3 -0
  23. model-00020-of-00023.safetensors +3 -0
  24. model-00021-of-00023.safetensors +3 -0
  25. model-00022-of-00023.safetensors +3 -0
  26. model-00023-of-00023.safetensors +3 -0
  27. 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 +1,609 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Llama4ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 200080,
6
+ "eoi_token_index": 200081,
7
+ "image_token_index": 200092,
8
+ "model_type": "llama4",
9
+ "quantization_config": {
10
+ "activation_scale_ub": 1200.0,
11
+ "modules_to_not_convert": [
12
+ "vision_model.patch_embedding.linear",
13
+ "vision_model.model.layers.0.self_attn.q_proj",
14
+ "vision_model.model.layers.0.self_attn.k_proj",
15
+ "vision_model.model.layers.0.self_attn.v_proj",
16
+ "vision_model.model.layers.0.self_attn.o_proj",
17
+ "vision_model.model.layers.0.mlp.fc1",
18
+ "vision_model.model.layers.0.mlp.fc2",
19
+ "vision_model.model.layers.1.self_attn.q_proj",
20
+ "vision_model.model.layers.1.self_attn.k_proj",
21
+ "vision_model.model.layers.1.self_attn.v_proj",
22
+ "vision_model.model.layers.1.self_attn.o_proj",
23
+ "vision_model.model.layers.1.mlp.fc1",
24
+ "vision_model.model.layers.1.mlp.fc2",
25
+ "vision_model.model.layers.2.self_attn.q_proj",
26
+ "vision_model.model.layers.2.self_attn.k_proj",
27
+ "vision_model.model.layers.2.self_attn.v_proj",
28
+ "vision_model.model.layers.2.self_attn.o_proj",
29
+ "vision_model.model.layers.2.mlp.fc1",
30
+ "vision_model.model.layers.2.mlp.fc2",
31
+ "vision_model.model.layers.3.self_attn.q_proj",
32
+ "vision_model.model.layers.3.self_attn.k_proj",
33
+ "vision_model.model.layers.3.self_attn.v_proj",
34
+ "vision_model.model.layers.3.self_attn.o_proj",
35
+ "vision_model.model.layers.3.mlp.fc1",
36
+ "vision_model.model.layers.3.mlp.fc2",
37
+ "vision_model.model.layers.4.self_attn.q_proj",
38
+ "vision_model.model.layers.4.self_attn.k_proj",
39
+ "vision_model.model.layers.4.self_attn.v_proj",
40
+ "vision_model.model.layers.4.self_attn.o_proj",
41
+ "vision_model.model.layers.4.mlp.fc1",
42
+ "vision_model.model.layers.4.mlp.fc2",
43
+ "vision_model.model.layers.5.self_attn.q_proj",
44
+ "vision_model.model.layers.5.self_attn.k_proj",
45
+ "vision_model.model.layers.5.self_attn.v_proj",
46
+ "vision_model.model.layers.5.self_attn.o_proj",
47
+ "vision_model.model.layers.5.mlp.fc1",
48
+ "vision_model.model.layers.5.mlp.fc2",
49
+ "vision_model.model.layers.6.self_attn.q_proj",
50
+ "vision_model.model.layers.6.self_attn.k_proj",
51
+ "vision_model.model.layers.6.self_attn.v_proj",
52
+ "vision_model.model.layers.6.self_attn.o_proj",
53
+ "vision_model.model.layers.6.mlp.fc1",
54
+ "vision_model.model.layers.6.mlp.fc2",
55
+ "vision_model.model.layers.7.self_attn.q_proj",
56
+ "vision_model.model.layers.7.self_attn.k_proj",
57
+ "vision_model.model.layers.7.self_attn.v_proj",
58
+ "vision_model.model.layers.7.self_attn.o_proj",
59
+ "vision_model.model.layers.7.mlp.fc1",
60
+ "vision_model.model.layers.7.mlp.fc2",
61
+ "vision_model.model.layers.8.self_attn.q_proj",
62
+ "vision_model.model.layers.8.self_attn.k_proj",
63
+ "vision_model.model.layers.8.self_attn.v_proj",
64
+ "vision_model.model.layers.8.self_attn.o_proj",
65
+ "vision_model.model.layers.8.mlp.fc1",
66
+ "vision_model.model.layers.8.mlp.fc2",
67
+ "vision_model.model.layers.9.self_attn.q_proj",
68
+ "vision_model.model.layers.9.self_attn.k_proj",
69
+ "vision_model.model.layers.9.self_attn.v_proj",
70
+ "vision_model.model.layers.9.self_attn.o_proj",
71
+ "vision_model.model.layers.9.mlp.fc1",
72
+ "vision_model.model.layers.9.mlp.fc2",
73
+ "vision_model.model.layers.10.self_attn.q_proj",
74
+ "vision_model.model.layers.10.self_attn.k_proj",
75
+ "vision_model.model.layers.10.self_attn.v_proj",
76
+ "vision_model.model.layers.10.self_attn.o_proj",
77
+ "vision_model.model.layers.10.mlp.fc1",
78
+ "vision_model.model.layers.10.mlp.fc2",
79
+ "vision_model.model.layers.11.self_attn.q_proj",
80
+ "vision_model.model.layers.11.self_attn.k_proj",
81
+ "vision_model.model.layers.11.self_attn.v_proj",
82
+ "vision_model.model.layers.11.self_attn.o_proj",
83
+ "vision_model.model.layers.11.mlp.fc1",
84
+ "vision_model.model.layers.11.mlp.fc2",
85
+ "vision_model.model.layers.12.self_attn.q_proj",
86
+ "vision_model.model.layers.12.self_attn.k_proj",
87
+ "vision_model.model.layers.12.self_attn.v_proj",
88
+ "vision_model.model.layers.12.self_attn.o_proj",
89
+ "vision_model.model.layers.12.mlp.fc1",
90
+ "vision_model.model.layers.12.mlp.fc2",
91
+ "vision_model.model.layers.13.self_attn.q_proj",
92
+ "vision_model.model.layers.13.self_attn.k_proj",
93
+ "vision_model.model.layers.13.self_attn.v_proj",
94
+ "vision_model.model.layers.13.self_attn.o_proj",
95
+ "vision_model.model.layers.13.mlp.fc1",
96
+ "vision_model.model.layers.13.mlp.fc2",
97
+ "vision_model.model.layers.14.self_attn.q_proj",
98
+ "vision_model.model.layers.14.self_attn.k_proj",
99
+ "vision_model.model.layers.14.self_attn.v_proj",
100
+ "vision_model.model.layers.14.self_attn.o_proj",
101
+ "vision_model.model.layers.14.mlp.fc1",
102
+ "vision_model.model.layers.14.mlp.fc2",
103
+ "vision_model.model.layers.15.self_attn.q_proj",
104
+ "vision_model.model.layers.15.self_attn.k_proj",
105
+ "vision_model.model.layers.15.self_attn.v_proj",
106
+ "vision_model.model.layers.15.self_attn.o_proj",
107
+ "vision_model.model.layers.15.mlp.fc1",
108
+ "vision_model.model.layers.15.mlp.fc2",
109
+ "vision_model.model.layers.16.self_attn.q_proj",
110
+ "vision_model.model.layers.16.self_attn.k_proj",
111
+ "vision_model.model.layers.16.self_attn.v_proj",
112
+ "vision_model.model.layers.16.self_attn.o_proj",
113
+ "vision_model.model.layers.16.mlp.fc1",
114
+ "vision_model.model.layers.16.mlp.fc2",
115
+ "vision_model.model.layers.17.self_attn.q_proj",
116
+ "vision_model.model.layers.17.self_attn.k_proj",
117
+ "vision_model.model.layers.17.self_attn.v_proj",
118
+ "vision_model.model.layers.17.self_attn.o_proj",
119
+ "vision_model.model.layers.17.mlp.fc1",
120
+ "vision_model.model.layers.17.mlp.fc2",
121
+ "vision_model.model.layers.18.self_attn.q_proj",
122
+ "vision_model.model.layers.18.self_attn.k_proj",
123
+ "vision_model.model.layers.18.self_attn.v_proj",
124
+ "vision_model.model.layers.18.self_attn.o_proj",
125
+ "vision_model.model.layers.18.mlp.fc1",
126
+ "vision_model.model.layers.18.mlp.fc2",
127
+ "vision_model.model.layers.19.self_attn.q_proj",
128
+ "vision_model.model.layers.19.self_attn.k_proj",
129
+ "vision_model.model.layers.19.self_attn.v_proj",
130
+ "vision_model.model.layers.19.self_attn.o_proj",
131
+ "vision_model.model.layers.19.mlp.fc1",
132
+ "vision_model.model.layers.19.mlp.fc2",
133
+ "vision_model.model.layers.20.self_attn.q_proj",
134
+ "vision_model.model.layers.20.self_attn.k_proj",
135
+ "vision_model.model.layers.20.self_attn.v_proj",
136
+ "vision_model.model.layers.20.self_attn.o_proj",
137
+ "vision_model.model.layers.20.mlp.fc1",
138
+ "vision_model.model.layers.20.mlp.fc2",
139
+ "vision_model.model.layers.21.self_attn.q_proj",
140
+ "vision_model.model.layers.21.self_attn.k_proj",
141
+ "vision_model.model.layers.21.self_attn.v_proj",
142
+ "vision_model.model.layers.21.self_attn.o_proj",
143
+ "vision_model.model.layers.21.mlp.fc1",
144
+ "vision_model.model.layers.21.mlp.fc2",
145
+ "vision_model.model.layers.22.self_attn.q_proj",
146
+ "vision_model.model.layers.22.self_attn.k_proj",
147
+ "vision_model.model.layers.22.self_attn.v_proj",
148
+ "vision_model.model.layers.22.self_attn.o_proj",
149
+ "vision_model.model.layers.22.mlp.fc1",
150
+ "vision_model.model.layers.22.mlp.fc2",
151
+ "vision_model.model.layers.23.self_attn.q_proj",
152
+ "vision_model.model.layers.23.self_attn.k_proj",
153
+ "vision_model.model.layers.23.self_attn.v_proj",
154
+ "vision_model.model.layers.23.self_attn.o_proj",
155
+ "vision_model.model.layers.23.mlp.fc1",
156
+ "vision_model.model.layers.23.mlp.fc2",
157
+ "vision_model.model.layers.24.self_attn.q_proj",
158
+ "vision_model.model.layers.24.self_attn.k_proj",
159
+ "vision_model.model.layers.24.self_attn.v_proj",
160
+ "vision_model.model.layers.24.self_attn.o_proj",
161
+ "vision_model.model.layers.24.mlp.fc1",
162
+ "vision_model.model.layers.24.mlp.fc2",
163
+ "vision_model.model.layers.25.self_attn.q_proj",
164
+ "vision_model.model.layers.25.self_attn.k_proj",
165
+ "vision_model.model.layers.25.self_attn.v_proj",
166
+ "vision_model.model.layers.25.self_attn.o_proj",
167
+ "vision_model.model.layers.25.mlp.fc1",
168
+ "vision_model.model.layers.25.mlp.fc2",
169
+ "vision_model.model.layers.26.self_attn.q_proj",
170
+ "vision_model.model.layers.26.self_attn.k_proj",
171
+ "vision_model.model.layers.26.self_attn.v_proj",
172
+ "vision_model.model.layers.26.self_attn.o_proj",
173
+ "vision_model.model.layers.26.mlp.fc1",
174
+ "vision_model.model.layers.26.mlp.fc2",
175
+ "vision_model.model.layers.27.self_attn.q_proj",
176
+ "vision_model.model.layers.27.self_attn.k_proj",
177
+ "vision_model.model.layers.27.self_attn.v_proj",
178
+ "vision_model.model.layers.27.self_attn.o_proj",
179
+ "vision_model.model.layers.27.mlp.fc1",
180
+ "vision_model.model.layers.27.mlp.fc2",
181
+ "vision_model.model.layers.28.self_attn.q_proj",
182
+ "vision_model.model.layers.28.self_attn.k_proj",
183
+ "vision_model.model.layers.28.self_attn.v_proj",
184
+ "vision_model.model.layers.28.self_attn.o_proj",
185
+ "vision_model.model.layers.28.mlp.fc1",
186
+ "vision_model.model.layers.28.mlp.fc2",
187
+ "vision_model.model.layers.29.self_attn.q_proj",
188
+ "vision_model.model.layers.29.self_attn.k_proj",
189
+ "vision_model.model.layers.29.self_attn.v_proj",
190
+ "vision_model.model.layers.29.self_attn.o_proj",
191
+ "vision_model.model.layers.29.mlp.fc1",
192
+ "vision_model.model.layers.29.mlp.fc2",
193
+ "vision_model.model.layers.30.self_attn.q_proj",
194
+ "vision_model.model.layers.30.self_attn.k_proj",
195
+ "vision_model.model.layers.30.self_attn.v_proj",
196
+ "vision_model.model.layers.30.self_attn.o_proj",
197
+ "vision_model.model.layers.30.mlp.fc1",
198
+ "vision_model.model.layers.30.mlp.fc2",
199
+ "vision_model.model.layers.31.self_attn.q_proj",
200
+ "vision_model.model.layers.31.self_attn.k_proj",
201
+ "vision_model.model.layers.31.self_attn.v_proj",
202
+ "vision_model.model.layers.31.self_attn.o_proj",
203
+ "vision_model.model.layers.31.mlp.fc1",
204
+ "vision_model.model.layers.31.mlp.fc2",
205
+ "vision_model.model.layers.32.self_attn.q_proj",
206
+ "vision_model.model.layers.32.self_attn.k_proj",
207
+ "vision_model.model.layers.32.self_attn.v_proj",
208
+ "vision_model.model.layers.32.self_attn.o_proj",
209
+ "vision_model.model.layers.32.mlp.fc1",
210
+ "vision_model.model.layers.32.mlp.fc2",
211
+ "vision_model.model.layers.33.self_attn.q_proj",
212
+ "vision_model.model.layers.33.self_attn.k_proj",
213
+ "vision_model.model.layers.33.self_attn.v_proj",
214
+ "vision_model.model.layers.33.self_attn.o_proj",
215
+ "vision_model.model.layers.33.mlp.fc1",
216
+ "vision_model.model.layers.33.mlp.fc2",
217
+ "vision_model.vision_adapter.mlp.fc1",
218
+ "vision_model.vision_adapter.mlp.fc2",
219
+ "multi_modal_projector.linear_1",
220
+ "language_model.lm_head",
221
+ "vision_model.patch_embedding.linear",
222
+ "vision_model.model.layers.0.self_attn.q_proj",
223
+ "vision_model.model.layers.0.self_attn.k_proj",
224
+ "vision_model.model.layers.0.self_attn.v_proj",
225
+ "vision_model.model.layers.0.self_attn.o_proj",
226
+ "vision_model.model.layers.0.mlp.fc1",
227
+ "vision_model.model.layers.0.mlp.fc2",
228
+ "vision_model.model.layers.1.self_attn.q_proj",
229
+ "vision_model.model.layers.1.self_attn.k_proj",
230
+ "vision_model.model.layers.1.self_attn.v_proj",
231
+ "vision_model.model.layers.1.self_attn.o_proj",
232
+ "vision_model.model.layers.1.mlp.fc1",
233
+ "vision_model.model.layers.1.mlp.fc2",
234
+ "vision_model.model.layers.2.self_attn.q_proj",
235
+ "vision_model.model.layers.2.self_attn.k_proj",
236
+ "vision_model.model.layers.2.self_attn.v_proj",
237
+ "vision_model.model.layers.2.self_attn.o_proj",
238
+ "vision_model.model.layers.2.mlp.fc1",
239
+ "vision_model.model.layers.2.mlp.fc2",
240
+ "vision_model.model.layers.3.self_attn.q_proj",
241
+ "vision_model.model.layers.3.self_attn.k_proj",
242
+ "vision_model.model.layers.3.self_attn.v_proj",
243
+ "vision_model.model.layers.3.self_attn.o_proj",
244
+ "vision_model.model.layers.3.mlp.fc1",
245
+ "vision_model.model.layers.3.mlp.fc2",
246
+ "vision_model.model.layers.4.self_attn.q_proj",
247
+ "vision_model.model.layers.4.self_attn.k_proj",
248
+ "vision_model.model.layers.4.self_attn.v_proj",
249
+ "vision_model.model.layers.4.self_attn.o_proj",
250
+ "vision_model.model.layers.4.mlp.fc1",
251
+ "vision_model.model.layers.4.mlp.fc2",
252
+ "vision_model.model.layers.5.self_attn.q_proj",
253
+ "vision_model.model.layers.5.self_attn.k_proj",
254
+ "vision_model.model.layers.5.self_attn.v_proj",
255
+ "vision_model.model.layers.5.self_attn.o_proj",
256
+ "vision_model.model.layers.5.mlp.fc1",
257
+ "vision_model.model.layers.5.mlp.fc2",
258
+ "vision_model.model.layers.6.self_attn.q_proj",
259
+ "vision_model.model.layers.6.self_attn.k_proj",
260
+ "vision_model.model.layers.6.self_attn.v_proj",
261
+ "vision_model.model.layers.6.self_attn.o_proj",
262
+ "vision_model.model.layers.6.mlp.fc1",
263
+ "vision_model.model.layers.6.mlp.fc2",
264
+ "vision_model.model.layers.7.self_attn.q_proj",
265
+ "vision_model.model.layers.7.self_attn.k_proj",
266
+ "vision_model.model.layers.7.self_attn.v_proj",
267
+ "vision_model.model.layers.7.self_attn.o_proj",
268
+ "vision_model.model.layers.7.mlp.fc1",
269
+ "vision_model.model.layers.7.mlp.fc2",
270
+ "vision_model.model.layers.8.self_attn.q_proj",
271
+ "vision_model.model.layers.8.self_attn.k_proj",
272
+ "vision_model.model.layers.8.self_attn.v_proj",
273
+ "vision_model.model.layers.8.self_attn.o_proj",
274
+ "vision_model.model.layers.8.mlp.fc1",
275
+ "vision_model.model.layers.8.mlp.fc2",
276
+ "vision_model.model.layers.9.self_attn.q_proj",
277
+ "vision_model.model.layers.9.self_attn.k_proj",
278
+ "vision_model.model.layers.9.self_attn.v_proj",
279
+ "vision_model.model.layers.9.self_attn.o_proj",
280
+ "vision_model.model.layers.9.mlp.fc1",
281
+ "vision_model.model.layers.9.mlp.fc2",
282
+ "vision_model.model.layers.10.self_attn.q_proj",
283
+ "vision_model.model.layers.10.self_attn.k_proj",
284
+ "vision_model.model.layers.10.self_attn.v_proj",
285
+ "vision_model.model.layers.10.self_attn.o_proj",
286
+ "vision_model.model.layers.10.mlp.fc1",
287
+ "vision_model.model.layers.10.mlp.fc2",
288
+ "vision_model.model.layers.11.self_attn.q_proj",
289
+ "vision_model.model.layers.11.self_attn.k_proj",
290
+ "vision_model.model.layers.11.self_attn.v_proj",
291
+ "vision_model.model.layers.11.self_attn.o_proj",
292
+ "vision_model.model.layers.11.mlp.fc1",
293
+ "vision_model.model.layers.11.mlp.fc2",
294
+ "vision_model.model.layers.12.self_attn.q_proj",
295
+ "vision_model.model.layers.12.self_attn.k_proj",
296
+ "vision_model.model.layers.12.self_attn.v_proj",
297
+ "vision_model.model.layers.12.self_attn.o_proj",
298
+ "vision_model.model.layers.12.mlp.fc1",
299
+ "vision_model.model.layers.12.mlp.fc2",
300
+ "vision_model.model.layers.13.self_attn.q_proj",
301
+ "vision_model.model.layers.13.self_attn.k_proj",
302
+ "vision_model.model.layers.13.self_attn.v_proj",
303
+ "vision_model.model.layers.13.self_attn.o_proj",
304
+ "vision_model.model.layers.13.mlp.fc1",
305
+ "vision_model.model.layers.13.mlp.fc2",
306
+ "vision_model.model.layers.14.self_attn.q_proj",
307
+ "vision_model.model.layers.14.self_attn.k_proj",
308
+ "vision_model.model.layers.14.self_attn.v_proj",
309
+ "vision_model.model.layers.14.self_attn.o_proj",
310
+ "vision_model.model.layers.14.mlp.fc1",
311
+ "vision_model.model.layers.14.mlp.fc2",
312
+ "vision_model.model.layers.15.self_attn.q_proj",
313
+ "vision_model.model.layers.15.self_attn.k_proj",
314
+ "vision_model.model.layers.15.self_attn.v_proj",
315
+ "vision_model.model.layers.15.self_attn.o_proj",
316
+ "vision_model.model.layers.15.mlp.fc1",
317
+ "vision_model.model.layers.15.mlp.fc2",
318
+ "vision_model.model.layers.16.self_attn.q_proj",
319
+ "vision_model.model.layers.16.self_attn.k_proj",
320
+ "vision_model.model.layers.16.self_attn.v_proj",
321
+ "vision_model.model.layers.16.self_attn.o_proj",
322
+ "vision_model.model.layers.16.mlp.fc1",
323
+ "vision_model.model.layers.16.mlp.fc2",
324
+ "vision_model.model.layers.17.self_attn.q_proj",
325
+ "vision_model.model.layers.17.self_attn.k_proj",
326
+ "vision_model.model.layers.17.self_attn.v_proj",
327
+ "vision_model.model.layers.17.self_attn.o_proj",
328
+ "vision_model.model.layers.17.mlp.fc1",
329
+ "vision_model.model.layers.17.mlp.fc2",
330
+ "vision_model.model.layers.18.self_attn.q_proj",
331
+ "vision_model.model.layers.18.self_attn.k_proj",
332
+ "vision_model.model.layers.18.self_attn.v_proj",
333
+ "vision_model.model.layers.18.self_attn.o_proj",
334
+ "vision_model.model.layers.18.mlp.fc1",
335
+ "vision_model.model.layers.18.mlp.fc2",
336
+ "vision_model.model.layers.19.self_attn.q_proj",
337
+ "vision_model.model.layers.19.self_attn.k_proj",
338
+ "vision_model.model.layers.19.self_attn.v_proj",
339
+ "vision_model.model.layers.19.self_attn.o_proj",
340
+ "vision_model.model.layers.19.mlp.fc1",
341
+ "vision_model.model.layers.19.mlp.fc2",
342
+ "vision_model.model.layers.20.self_attn.q_proj",
343
+ "vision_model.model.layers.20.self_attn.k_proj",
344
+ "vision_model.model.layers.20.self_attn.v_proj",
345
+ "vision_model.model.layers.20.self_attn.o_proj",
346
+ "vision_model.model.layers.20.mlp.fc1",
347
+ "vision_model.model.layers.20.mlp.fc2",
348
+ "vision_model.model.layers.21.self_attn.q_proj",
349
+ "vision_model.model.layers.21.self_attn.k_proj",
350
+ "vision_model.model.layers.21.self_attn.v_proj",
351
+ "vision_model.model.layers.21.self_attn.o_proj",
352
+ "vision_model.model.layers.21.mlp.fc1",
353
+ "vision_model.model.layers.21.mlp.fc2",
354
+ "vision_model.model.layers.22.self_attn.q_proj",
355
+ "vision_model.model.layers.22.self_attn.k_proj",
356
+ "vision_model.model.layers.22.self_attn.v_proj",
357
+ "vision_model.model.layers.22.self_attn.o_proj",
358
+ "vision_model.model.layers.22.mlp.fc1",
359
+ "vision_model.model.layers.22.mlp.fc2",
360
+ "vision_model.model.layers.23.self_attn.q_proj",
361
+ "vision_model.model.layers.23.self_attn.k_proj",
362
+ "vision_model.model.layers.23.self_attn.v_proj",
363
+ "vision_model.model.layers.23.self_attn.o_proj",
364
+ "vision_model.model.layers.23.mlp.fc1",
365
+ "vision_model.model.layers.23.mlp.fc2",
366
+ "vision_model.model.layers.24.self_attn.q_proj",
367
+ "vision_model.model.layers.24.self_attn.k_proj",
368
+ "vision_model.model.layers.24.self_attn.v_proj",
369
+ "vision_model.model.layers.24.self_attn.o_proj",
370
+ "vision_model.model.layers.24.mlp.fc1",
371
+ "vision_model.model.layers.24.mlp.fc2",
372
+ "vision_model.model.layers.25.self_attn.q_proj",
373
+ "vision_model.model.layers.25.self_attn.k_proj",
374
+ "vision_model.model.layers.25.self_attn.v_proj",
375
+ "vision_model.model.layers.25.self_attn.o_proj",
376
+ "vision_model.model.layers.25.mlp.fc1",
377
+ "vision_model.model.layers.25.mlp.fc2",
378
+ "vision_model.model.layers.26.self_attn.q_proj",
379
+ "vision_model.model.layers.26.self_attn.k_proj",
380
+ "vision_model.model.layers.26.self_attn.v_proj",
381
+ "vision_model.model.layers.26.self_attn.o_proj",
382
+ "vision_model.model.layers.26.mlp.fc1",
383
+ "vision_model.model.layers.26.mlp.fc2",
384
+ "vision_model.model.layers.27.self_attn.q_proj",
385
+ "vision_model.model.layers.27.self_attn.k_proj",
386
+ "vision_model.model.layers.27.self_attn.v_proj",
387
+ "vision_model.model.layers.27.self_attn.o_proj",
388
+ "vision_model.model.layers.27.mlp.fc1",
389
+ "vision_model.model.layers.27.mlp.fc2",
390
+ "vision_model.model.layers.28.self_attn.q_proj",
391
+ "vision_model.model.layers.28.self_attn.k_proj",
392
+ "vision_model.model.layers.28.self_attn.v_proj",
393
+ "vision_model.model.layers.28.self_attn.o_proj",
394
+ "vision_model.model.layers.28.mlp.fc1",
395
+ "vision_model.model.layers.28.mlp.fc2",
396
+ "vision_model.model.layers.29.self_attn.q_proj",
397
+ "vision_model.model.layers.29.self_attn.k_proj",
398
+ "vision_model.model.layers.29.self_attn.v_proj",
399
+ "vision_model.model.layers.29.self_attn.o_proj",
400
+ "vision_model.model.layers.29.mlp.fc1",
401
+ "vision_model.model.layers.29.mlp.fc2",
402
+ "vision_model.model.layers.30.self_attn.q_proj",
403
+ "vision_model.model.layers.30.self_attn.k_proj",
404
+ "vision_model.model.layers.30.self_attn.v_proj",
405
+ "vision_model.model.layers.30.self_attn.o_proj",
406
+ "vision_model.model.layers.30.mlp.fc1",
407
+ "vision_model.model.layers.30.mlp.fc2",
408
+ "vision_model.model.layers.31.self_attn.q_proj",
409
+ "vision_model.model.layers.31.self_attn.k_proj",
410
+ "vision_model.model.layers.31.self_attn.v_proj",
411
+ "vision_model.model.layers.31.self_attn.o_proj",
412
+ "vision_model.model.layers.31.mlp.fc1",
413
+ "vision_model.model.layers.31.mlp.fc2",
414
+ "vision_model.model.layers.32.self_attn.q_proj",
415
+ "vision_model.model.layers.32.self_attn.k_proj",
416
+ "vision_model.model.layers.32.self_attn.v_proj",
417
+ "vision_model.model.layers.32.self_attn.o_proj",
418
+ "vision_model.model.layers.32.mlp.fc1",
419
+ "vision_model.model.layers.32.mlp.fc2",
420
+ "vision_model.model.layers.33.self_attn.q_proj",
421
+ "vision_model.model.layers.33.self_attn.k_proj",
422
+ "vision_model.model.layers.33.self_attn.v_proj",
423
+ "vision_model.model.layers.33.self_attn.o_proj",
424
+ "vision_model.model.layers.33.mlp.fc1",
425
+ "vision_model.model.layers.33.mlp.fc2",
426
+ "vision_model.vision_adapter.mlp.fc1",
427
+ "vision_model.vision_adapter.mlp.fc2",
428
+ "multi_modal_projector.linear_1",
429
+ "language_model.lm_head"
430
+ ],
431
+ "quant_method": "fbgemm_fp8"
432
+ },
433
+ "text_config": {
434
+ "_attn_implementation_autoset": true,
435
+ "attention_bias": false,
436
+ "attention_chunk_size": 8192,
437
+ "attention_dropout": 0.0,
438
+ "attn_scale": 0.1,
439
+ "attn_temperature_tuning": 4,
440
+ "bos_token_id": 200000,
441
+ "cache_implementation": "hybrid",
442
+ "eos_token_id": [
443
+ 200001,
444
+ 200007,
445
+ 200008
446
+ ],
447
+ "floor_scale": 8192,
448
+ "for_llm_compressor": false,
449
+ "head_dim": 128,
450
+ "hidden_act": "silu",
451
+ "hidden_size": 5120,
452
+ "initializer_range": 0.02,
453
+ "interleave_moe_layer_step": 1,
454
+ "intermediate_size": 8192,
455
+ "intermediate_size_mlp": 16384,
456
+ "max_position_embeddings": 10485760,
457
+ "model_type": "llama4_text",
458
+ "moe_layers": [
459
+ 0,
460
+ 1,
461
+ 2,
462
+ 3,
463
+ 4,
464
+ 5,
465
+ 6,
466
+ 7,
467
+ 8,
468
+ 9,
469
+ 10,
470
+ 11,
471
+ 12,
472
+ 13,
473
+ 14,
474
+ 15,
475
+ 16,
476
+ 17,
477
+ 18,
478
+ 19,
479
+ 20,
480
+ 21,
481
+ 22,
482
+ 23,
483
+ 24,
484
+ 25,
485
+ 26,
486
+ 27,
487
+ 28,
488
+ 29,
489
+ 30,
490
+ 31,
491
+ 32,
492
+ 33,
493
+ 34,
494
+ 35,
495
+ 36,
496
+ 37,
497
+ 38,
498
+ 39,
499
+ 40,
500
+ 41,
501
+ 42,
502
+ 43,
503
+ 44,
504
+ 45,
505
+ 46,
506
+ 47
507
+ ],
508
+ "no_rope_layers": [
509
+ 1,
510
+ 1,
511
+ 1,
512
+ 0,
513
+ 1,
514
+ 1,
515
+ 1,
516
+ 0,
517
+ 1,
518
+ 1,
519
+ 1,
520
+ 0,
521
+ 1,
522
+ 1,
523
+ 1,
524
+ 0,
525
+ 1,
526
+ 1,
527
+ 1,
528
+ 0,
529
+ 1,
530
+ 1,
531
+ 1,
532
+ 0,
533
+ 1,
534
+ 1,
535
+ 1,
536
+ 0,
537
+ 1,
538
+ 1,
539
+ 1,
540
+ 0,
541
+ 1,
542
+ 1,
543
+ 1,
544
+ 0,
545
+ 1,
546
+ 1,
547
+ 1,
548
+ 0,
549
+ 1,
550
+ 1,
551
+ 1,
552
+ 0,
553
+ 1,
554
+ 1,
555
+ 1,
556
+ 0
557
+ ],
558
+ "num_attention_heads": 40,
559
+ "num_experts_per_tok": 1,
560
+ "num_hidden_layers": 48,
561
+ "num_key_value_heads": 8,
562
+ "num_local_experts": 16,
563
+ "output_router_logits": false,
564
+ "pad_token_id": 200018,
565
+ "rms_norm_eps": 1e-05,
566
+ "rope_scaling": {
567
+ "factor": 8.0,
568
+ "high_freq_factor": 4.0,
569
+ "low_freq_factor": 1.0,
570
+ "original_max_position_embeddings": 8192,
571
+ "rope_type": "llama3"
572
+ },
573
+ "rope_theta": 500000.0,
574
+ "router_aux_loss_coef": 0.001,
575
+ "router_jitter_noise": 0.0,
576
+ "torch_dtype": "bfloat16",
577
+ "use_cache": true,
578
+ "use_qk_norm": true,
579
+ "vocab_size": 202048
580
+ },
581
+ "tie_word_embeddings": false,
582
+ "torch_dtype": "bfloat16",
583
+ "transformers_version": "4.52.0.dev0",
584
+ "vision_config": {
585
+ "_attn_implementation_autoset": true,
586
+ "attention_dropout": 0.0,
587
+ "hidden_act": "gelu",
588
+ "hidden_size": 1408,
589
+ "image_size": 336,
590
+ "initializer_range": 0.02,
591
+ "intermediate_size": 5632,
592
+ "model_type": "llama4_vision_model",
593
+ "multi_modal_projector_bias": false,
594
+ "norm_eps": 1e-05,
595
+ "num_attention_heads": 16,
596
+ "num_channels": 3,
597
+ "num_hidden_layers": 34,
598
+ "patch_size": 14,
599
+ "pixel_shuffle_ratio": 0.5,
600
+ "projector_dropout": 0.0,
601
+ "projector_input_dim": 4096,
602
+ "projector_output_dim": 4096,
603
+ "rope_theta": 10000,
604
+ "torch_dtype": "bfloat16",
605
+ "vision_feature_layer": -1,
606
+ "vision_feature_select_strategy": "default",
607
+ "vision_output_dim": 4096
608
+ }
609
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 200000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200001,
6
+ 200007,
7
+ 200008
8
+ ],
9
+ "pad_token_id": 200018,
10
+ "temperature": 0.6,
11
+ "top_p": 0.9,
12
+ "transformers_version": "4.52.0.dev0"
13
+ }
model-00001-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187b94ee91f9ad480f46d3ad7b9690063fb95e071f5a5b361eb108bc53b26b56
3
+ size 4967150776
model-00002-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a5088932358de0c59f55f481e78395b8f6f33420987876f036eebb2a39d8ba
3
+ size 4994884096
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141fe464e892ff384bf0254f614591dda73d3b196b5cdd7f108fb4b9254f07f8
3
+ size 4974011936
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e1bc8795c772d53c3a6dc2eaf30767165b7adf2832078a68e3f76e688dd848
3
+ size 4994884072
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273baa7bc7a46668b1822cea598827f160ea4cf2d5dd5566995938783d53dee0
3
+ size 4994896360
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a839832f1b0f08b96046b6e5c554f658a151733c7c8edc2c8ec4e289795f68
3
+ size 4994884312
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b1c3c6676249064dc8d47477cc67adf7091f7b639765f5eca60d68a1eee40c
3
+ size 4974012192
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a60c9145e8171b9703c3566d490316512180f30c89b4421354a9bb59a644ff2
3
+ size 4994884328
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388a513e49d6219042c702615f97023dda0b8ef0af66c80afa35461e62e9bf15
3
+ size 4994896616
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28eea46bb0bdd531ba30150fedd8f4c22fba94a45a05e0cecab2f5baf79998a6
3
+ size 4994884360
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07a292e7472c5993f842314ad77b66ecb64a6ab411f3d519efc36886c416c40
3
+ size 4974012184
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2ed10ae26b6cb4952e6055fe0d2ed2535a5b32b9afac34c2dfa2cbab4a60c5e
3
+ size 4994884328
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ecdb0db3690045641a2efee56697adaf9fcd977b466ce4c6491f7f6bc9aef3
3
+ size 4994896624
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187a05f9fd2498ac3a0c4a0788f103f58c46a769088c52b4ae11b14263cb017e
3
+ size 4994966616
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d37014f31bb3063f004143eae2c846dfc214051ed976131a9c5e9c8770981b
3
+ size 4973929928
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe172421e515beaab145973f70514771ccdfcbc3a00276a4bc88bd7feee98f3
3
+ size 4994884328
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a616ebf3fcc6dcdb214af728cce395b2996aa734d41ea30d2695ca15f05643c7
3
+ size 4994896632
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46661820f6b61c8cc3a967627a282a6ea03872808be3c48c1d9fb90ea2b862e9
3
+ size 4989740880
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8226e71236b652df928f18e9081f6cbe9ec7bbfa17bab2d439d49f33387e273c
3
+ size 4979155664
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a4149bf06ebb42f0626d68bff93273c673cf1878e293e9761289479e750e10
3
+ size 4994884328
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce53e069433bb81806bab38b01f274d1850236927ae32859a7924681a2fde6d6
3
+ size 4994896632
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9307a8e1f7ccb6e795e6a03c893f4a4d4a5392cd418752fa8cd51543e60e5a40
3
+ size 4827105560
model-00023-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f412ae287747cc86e6ee5d58600bbe5c574d6fa77f351367aae9ea3f4dbcc3a
3
+ size 2068971664
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff