Teggyg commited on
Commit
b8095ea
1 Parent(s): 03ea5bd

Upload FluxPipeline

Browse files
README.md ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: diffusers
3
+ ---
4
+
5
+ # Model Card for Model ID
6
+
7
+ <!-- Provide a quick summary of what the model is/does. -->
8
+
9
+
10
+
11
+ ## Model Details
12
+
13
+ ### Model Description
14
+
15
+ <!-- Provide a longer summary of what this model is. -->
16
+
17
+ This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
18
+
19
+ - **Developed by:** [More Information Needed]
20
+ - **Funded by [optional]:** [More Information Needed]
21
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- 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. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Dataset Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ 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).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FluxPipeline",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "black-forest-labs/FLUX.1-schnell",
5
+ "scheduler": [
6
+ null,
7
+ null
8
+ ],
9
+ "text_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "text_encoder_2": [
14
+ "transformers",
15
+ "T5EncoderModel"
16
+ ],
17
+ "tokenizer": [
18
+ null,
19
+ null
20
+ ],
21
+ "tokenizer_2": [
22
+ null,
23
+ null
24
+ ],
25
+ "transformer": [
26
+ "diffusers",
27
+ "FluxTransformer2DModel"
28
+ ],
29
+ "vae": [
30
+ null,
31
+ null
32
+ ]
33
+ }
text_encoder_2/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "black-forest-labs/FLUX.1-schnell",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "quantization_config": {
26
+ "_load_in_4bit": false,
27
+ "_load_in_8bit": true,
28
+ "bnb_4bit_compute_dtype": "float32",
29
+ "bnb_4bit_quant_storage": "uint8",
30
+ "bnb_4bit_quant_type": "fp4",
31
+ "bnb_4bit_use_double_quant": false,
32
+ "llm_int8_enable_fp32_cpu_offload": false,
33
+ "llm_int8_has_fp16_weight": false,
34
+ "llm_int8_skip_modules": null,
35
+ "llm_int8_threshold": 6.0,
36
+ "load_in_4bit": false,
37
+ "load_in_8bit": true,
38
+ "quant_method": "bitsandbytes"
39
+ },
40
+ "relative_attention_max_distance": 128,
41
+ "relative_attention_num_buckets": 32,
42
+ "tie_word_embeddings": false,
43
+ "torch_dtype": "float16",
44
+ "transformers_version": "4.46.1",
45
+ "use_cache": true,
46
+ "vocab_size": 32128
47
+ }
text_encoder_2/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef473bea1e43fdbd98c5c4bcaabee00eb80735f447bc3217092b737a10983a31
3
+ size 4879418722
text_encoder_2/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b82b197a4465d746e13f9388f677f008fb2d2f282dc4f1dda03460f9532565a
3
+ size 3038190478
text_encoder_2/model.safetensors.index.json ADDED
@@ -0,0 +1,514 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7917547664
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
11
+ "encoder.block.0.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
12
+ "encoder.block.0.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
13
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
14
+ "encoder.block.0.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
15
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
16
+ "encoder.block.0.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
17
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
18
+ "encoder.block.0.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
19
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
20
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
21
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
22
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
23
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
24
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
25
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
26
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
27
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
28
+ "encoder.block.1.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
29
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
30
+ "encoder.block.1.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
31
+ "encoder.block.1.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
32
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
33
+ "encoder.block.1.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
34
+ "encoder.block.1.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
35
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
36
+ "encoder.block.1.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
37
+ "encoder.block.1.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
38
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
39
+ "encoder.block.1.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
40
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
41
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
42
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
43
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
44
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
45
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
46
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
47
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
48
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
49
+ "encoder.block.10.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
50
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
51
+ "encoder.block.10.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
52
+ "encoder.block.10.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
53
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
54
+ "encoder.block.10.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
55
+ "encoder.block.10.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
56
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
57
+ "encoder.block.10.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
58
+ "encoder.block.10.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
59
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
60
+ "encoder.block.10.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
61
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
62
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
63
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
64
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
65
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
66
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
67
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
68
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
69
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
70
+ "encoder.block.11.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
71
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
72
+ "encoder.block.11.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
73
+ "encoder.block.11.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
74
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
75
+ "encoder.block.11.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
76
+ "encoder.block.11.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
77
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
78
+ "encoder.block.11.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
79
+ "encoder.block.11.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
80
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
81
+ "encoder.block.11.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
82
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
83
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
84
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
85
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
86
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
87
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
88
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
89
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
90
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
91
+ "encoder.block.12.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
92
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
93
+ "encoder.block.12.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
94
+ "encoder.block.12.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
95
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
96
+ "encoder.block.12.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
97
+ "encoder.block.12.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
98
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
99
+ "encoder.block.12.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
100
+ "encoder.block.12.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
101
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
102
+ "encoder.block.12.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
103
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
104
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
105
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
106
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
107
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
108
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
109
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
110
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
111
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
112
+ "encoder.block.13.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
113
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
114
+ "encoder.block.13.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
115
+ "encoder.block.13.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
116
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
117
+ "encoder.block.13.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
118
+ "encoder.block.13.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
119
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
120
+ "encoder.block.13.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
121
+ "encoder.block.13.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
122
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
123
+ "encoder.block.13.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
124
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
125
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
126
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
127
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
128
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
129
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
130
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
131
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
132
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
133
+ "encoder.block.14.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
134
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
135
+ "encoder.block.14.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
136
+ "encoder.block.14.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
137
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
138
+ "encoder.block.14.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
139
+ "encoder.block.14.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
140
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
141
+ "encoder.block.14.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
142
+ "encoder.block.14.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
143
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
144
+ "encoder.block.14.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
145
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
146
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
147
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
148
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
149
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
150
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
151
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
152
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
153
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
154
+ "encoder.block.15.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
155
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
156
+ "encoder.block.15.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
157
+ "encoder.block.15.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
158
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
159
+ "encoder.block.15.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
160
+ "encoder.block.15.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
161
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
162
+ "encoder.block.15.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
163
+ "encoder.block.15.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
164
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
165
+ "encoder.block.15.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
166
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
167
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
168
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
169
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
170
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
171
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
172
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
173
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
174
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
175
+ "encoder.block.16.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
176
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
177
+ "encoder.block.16.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
178
+ "encoder.block.16.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
179
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
180
+ "encoder.block.16.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
181
+ "encoder.block.16.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
182
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
183
+ "encoder.block.16.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
184
+ "encoder.block.16.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
185
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
186
+ "encoder.block.16.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
187
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
188
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
189
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
190
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
191
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
192
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
193
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
194
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
195
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
196
+ "encoder.block.17.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
197
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
198
+ "encoder.block.17.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
199
+ "encoder.block.17.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
200
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
201
+ "encoder.block.17.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
202
+ "encoder.block.17.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
203
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
204
+ "encoder.block.17.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
205
+ "encoder.block.17.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
206
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
207
+ "encoder.block.17.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
208
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
209
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
210
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
211
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
212
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
213
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
214
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
215
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
216
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
217
+ "encoder.block.18.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
218
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
219
+ "encoder.block.18.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
220
+ "encoder.block.18.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
221
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
222
+ "encoder.block.18.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
223
+ "encoder.block.18.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
224
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
225
+ "encoder.block.18.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
226
+ "encoder.block.18.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
227
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
228
+ "encoder.block.18.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
229
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
230
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
231
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
232
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
233
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
234
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
235
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
236
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
237
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
238
+ "encoder.block.19.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
239
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
240
+ "encoder.block.19.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
241
+ "encoder.block.19.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
242
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
243
+ "encoder.block.19.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
244
+ "encoder.block.19.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
245
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
246
+ "encoder.block.19.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
247
+ "encoder.block.19.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
248
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
249
+ "encoder.block.19.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
250
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
251
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
252
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
253
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
254
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
255
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
256
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
257
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
258
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
259
+ "encoder.block.2.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
260
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
261
+ "encoder.block.2.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
262
+ "encoder.block.2.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
263
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
264
+ "encoder.block.2.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
265
+ "encoder.block.2.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
266
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
267
+ "encoder.block.2.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
268
+ "encoder.block.2.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
269
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
270
+ "encoder.block.2.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
271
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
272
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
273
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
274
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
275
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
276
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
277
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
278
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
279
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
280
+ "encoder.block.20.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
281
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
282
+ "encoder.block.20.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
283
+ "encoder.block.20.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
284
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
285
+ "encoder.block.20.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
286
+ "encoder.block.20.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
287
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
288
+ "encoder.block.20.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
289
+ "encoder.block.20.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
290
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
291
+ "encoder.block.20.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
292
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
293
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
294
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
295
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
296
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
297
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
298
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
299
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
300
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
301
+ "encoder.block.21.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
302
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
303
+ "encoder.block.21.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
304
+ "encoder.block.21.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
305
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
306
+ "encoder.block.21.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
307
+ "encoder.block.21.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
308
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
309
+ "encoder.block.21.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
310
+ "encoder.block.21.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
311
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
312
+ "encoder.block.21.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
313
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
314
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
315
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
316
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
317
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
318
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
319
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
320
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
321
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
322
+ "encoder.block.22.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
323
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
324
+ "encoder.block.22.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
325
+ "encoder.block.22.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
326
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
327
+ "encoder.block.22.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
328
+ "encoder.block.22.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
329
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
330
+ "encoder.block.22.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
331
+ "encoder.block.22.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
332
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
333
+ "encoder.block.22.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
334
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
335
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
336
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
337
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
338
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
339
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
340
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
341
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
342
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
343
+ "encoder.block.23.layer.0.SelfAttention.k.SCB": "model-00002-of-00002.safetensors",
344
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
345
+ "encoder.block.23.layer.0.SelfAttention.k.weight_format": "model-00002-of-00002.safetensors",
346
+ "encoder.block.23.layer.0.SelfAttention.o.SCB": "model-00002-of-00002.safetensors",
347
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
348
+ "encoder.block.23.layer.0.SelfAttention.o.weight_format": "model-00002-of-00002.safetensors",
349
+ "encoder.block.23.layer.0.SelfAttention.q.SCB": "model-00002-of-00002.safetensors",
350
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
351
+ "encoder.block.23.layer.0.SelfAttention.q.weight_format": "model-00002-of-00002.safetensors",
352
+ "encoder.block.23.layer.0.SelfAttention.v.SCB": "model-00002-of-00002.safetensors",
353
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
354
+ "encoder.block.23.layer.0.SelfAttention.v.weight_format": "model-00002-of-00002.safetensors",
355
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
356
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.SCB": "model-00002-of-00002.safetensors",
357
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
358
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight_format": "model-00002-of-00002.safetensors",
359
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.SCB": "model-00002-of-00002.safetensors",
360
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
361
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight_format": "model-00002-of-00002.safetensors",
362
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
363
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
364
+ "encoder.block.3.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
365
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
366
+ "encoder.block.3.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
367
+ "encoder.block.3.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
368
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
369
+ "encoder.block.3.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
370
+ "encoder.block.3.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
371
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
372
+ "encoder.block.3.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
373
+ "encoder.block.3.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
374
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
375
+ "encoder.block.3.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
376
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
377
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
378
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
379
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
380
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
381
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
382
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
383
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
384
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
385
+ "encoder.block.4.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
386
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
387
+ "encoder.block.4.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
388
+ "encoder.block.4.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
389
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
390
+ "encoder.block.4.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
391
+ "encoder.block.4.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
392
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
393
+ "encoder.block.4.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
394
+ "encoder.block.4.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
395
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
396
+ "encoder.block.4.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
397
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
398
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
399
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
400
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
401
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
402
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
403
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
404
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
405
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
406
+ "encoder.block.5.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
407
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
408
+ "encoder.block.5.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
409
+ "encoder.block.5.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
410
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
411
+ "encoder.block.5.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
412
+ "encoder.block.5.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
413
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
414
+ "encoder.block.5.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
415
+ "encoder.block.5.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
416
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
417
+ "encoder.block.5.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
418
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
419
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
420
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
421
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
422
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
423
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
424
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
425
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
426
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
427
+ "encoder.block.6.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
428
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
429
+ "encoder.block.6.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
430
+ "encoder.block.6.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
431
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
432
+ "encoder.block.6.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
433
+ "encoder.block.6.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
434
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
435
+ "encoder.block.6.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
436
+ "encoder.block.6.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
437
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
438
+ "encoder.block.6.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
439
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
440
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
441
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
442
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
443
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
444
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
445
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
446
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
447
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
448
+ "encoder.block.7.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
449
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
450
+ "encoder.block.7.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
451
+ "encoder.block.7.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
452
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
453
+ "encoder.block.7.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
454
+ "encoder.block.7.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
455
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
456
+ "encoder.block.7.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
457
+ "encoder.block.7.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
458
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
459
+ "encoder.block.7.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
460
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
461
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
462
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
463
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
464
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
465
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
466
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
467
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
468
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
469
+ "encoder.block.8.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
470
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
471
+ "encoder.block.8.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
472
+ "encoder.block.8.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
473
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
474
+ "encoder.block.8.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
475
+ "encoder.block.8.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
476
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
477
+ "encoder.block.8.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
478
+ "encoder.block.8.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
479
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
480
+ "encoder.block.8.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
481
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
482
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
483
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
484
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
485
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
486
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
487
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
488
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
489
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
490
+ "encoder.block.9.layer.0.SelfAttention.k.SCB": "model-00001-of-00002.safetensors",
491
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
492
+ "encoder.block.9.layer.0.SelfAttention.k.weight_format": "model-00001-of-00002.safetensors",
493
+ "encoder.block.9.layer.0.SelfAttention.o.SCB": "model-00001-of-00002.safetensors",
494
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
495
+ "encoder.block.9.layer.0.SelfAttention.o.weight_format": "model-00001-of-00002.safetensors",
496
+ "encoder.block.9.layer.0.SelfAttention.q.SCB": "model-00001-of-00002.safetensors",
497
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
498
+ "encoder.block.9.layer.0.SelfAttention.q.weight_format": "model-00001-of-00002.safetensors",
499
+ "encoder.block.9.layer.0.SelfAttention.v.SCB": "model-00001-of-00002.safetensors",
500
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
501
+ "encoder.block.9.layer.0.SelfAttention.v.weight_format": "model-00001-of-00002.safetensors",
502
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
503
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.SCB": "model-00001-of-00002.safetensors",
504
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
505
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight_format": "model-00001-of-00002.safetensors",
506
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.SCB": "model-00001-of-00002.safetensors",
507
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
508
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight_format": "model-00001-of-00002.safetensors",
509
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
510
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
511
+ "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
512
+ "shared.weight": "model-00001-of-00002.safetensors"
513
+ }
514
+ }
transformer/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FluxTransformer2DModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "black-forest-labs/FLUX.1-schnell",
5
+ "attention_head_dim": 128,
6
+ "axes_dims_rope": [
7
+ 16,
8
+ 56,
9
+ 56
10
+ ],
11
+ "guidance_embeds": false,
12
+ "in_channels": 64,
13
+ "joint_attention_dim": 4096,
14
+ "num_attention_heads": 24,
15
+ "num_layers": 19,
16
+ "num_single_layers": 38,
17
+ "patch_size": 1,
18
+ "pooled_projection_dim": 768,
19
+ "quantization_config": {
20
+ "_load_in_4bit": false,
21
+ "_load_in_8bit": true,
22
+ "bnb_4bit_compute_dtype": "float32",
23
+ "bnb_4bit_quant_storage": "uint8",
24
+ "bnb_4bit_quant_type": "fp4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": false,
31
+ "load_in_8bit": true,
32
+ "quant_method": "bitsandbytes"
33
+ }
34
+ }
transformer/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e240b903d4da2ca4a7c4c3524c6875ed87eb47efb81bc051a9620c8672842e4
3
+ size 9969128178
transformer/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0a8cc49b006873b9b6dbba3c4c9a9f83abacff6898060f8bc41f7bdc347b89
3
+ size 1937614876
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff