lhallee commited on
Commit
628366e
·
verified ·
1 Parent(s): aca7442

Upload BoltzGen

Browse files
Files changed (3) hide show
  1. README.md +199 -0
  2. config.json +232 -0
  3. pytorch_model.bin +3 -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 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "affinity_baseline": false,
3
+ "affinity_confidence_different": false,
4
+ "affinity_confidence_different_multiple": false,
5
+ "affinity_ensemble": false,
6
+ "affinity_model_args": {
7
+ "affinity_args": {
8
+ "groups": {
9
+ "0": 1
10
+ },
11
+ "val_groups": [
12
+ 0
13
+ ]
14
+ }
15
+ },
16
+ "affinity_model_args1": {},
17
+ "affinity_model_args2": {},
18
+ "affinity_mw_correction": true,
19
+ "affinity_pair_transformer": false,
20
+ "affinity_prediction": false,
21
+ "affinity_transformer": false,
22
+ "affinity_transformer_atom": false,
23
+ "alpha_affinity_absolute": 0.0,
24
+ "alpha_affinity_binary": 0.0,
25
+ "alpha_affinity_difference": 0.0,
26
+ "alpha_affinity_focal": 0.0,
27
+ "alpha_affinity_score_binder_binder": 0.0,
28
+ "alpha_affinity_score_binder_decoy": 0.0,
29
+ "alpha_pae": 1,
30
+ "architectures": [
31
+ "BoltzGen"
32
+ ],
33
+ "atom_feature_dim": 388,
34
+ "atom_s": 128,
35
+ "atom_z": 16,
36
+ "atoms_per_window_keys": 128,
37
+ "atoms_per_window_queries": 32,
38
+ "bond_type_feature": true,
39
+ "chain_sampling_args": null,
40
+ "checkpoint_diffusion_conditioning": true,
41
+ "compile_confidence": false,
42
+ "compile_msa": false,
43
+ "compile_pairformer": false,
44
+ "compile_structure": false,
45
+ "compile_templates": false,
46
+ "compute_tistogram": false,
47
+ "confidence_imitate_trunk": false,
48
+ "confidence_model_args": {
49
+ "add_s_input_to_s": true,
50
+ "add_s_to_z_prod": true,
51
+ "add_z_input_to_z": true,
52
+ "confidence_args": {
53
+ "num_pae_bins": 64,
54
+ "num_pde_bins": 64,
55
+ "num_plddt_bins": 50,
56
+ "relative_confidence": "none",
57
+ "use_separate_heads": true
58
+ },
59
+ "max_dist": 22,
60
+ "no_trunk_feats": false,
61
+ "num_dist_bins": 64,
62
+ "pairformer_args": {
63
+ "dropout": 0.25,
64
+ "num_blocks": 8,
65
+ "num_heads": 16
66
+ },
67
+ "use_gaussian": false,
68
+ "use_miniformer": false,
69
+ "use_s_diffusion": false
70
+ },
71
+ "confidence_prediction": true,
72
+ "confidence_regression": false,
73
+ "cyclic_pos_enc": true,
74
+ "diffusion_loss_args": {
75
+ "add_bond_loss": false,
76
+ "add_smooth_lddt_loss": true,
77
+ "filter_by_plddt": 0.0,
78
+ "ligand_loss_weight": 10.0,
79
+ "nucleotide_loss_weight": 5.0
80
+ },
81
+ "diffusion_process_args": {
82
+ "P_mean": -1.2,
83
+ "P_std": 1.5,
84
+ "alignment_reverse_diff": true,
85
+ "coordinate_augmentation": true,
86
+ "gamma_0": 0.8,
87
+ "gamma_min": 1.0,
88
+ "mse_rotational_alignment": true,
89
+ "noise_scale": 1.0,
90
+ "rho": 7,
91
+ "sigma_data": 16.0,
92
+ "sigma_max": 160.0,
93
+ "sigma_min": 0.0004,
94
+ "step_scale": 1.0,
95
+ "step_scale_random": [
96
+ 1.0,
97
+ 1.1,
98
+ 1.2,
99
+ 1.3,
100
+ 1.4,
101
+ 1.5
102
+ ],
103
+ "synchronize_sigmas": false
104
+ },
105
+ "dtype": "float32",
106
+ "dynamic_args": {},
107
+ "ema": true,
108
+ "ema_decay": 0.999,
109
+ "embedder_args": {
110
+ "add_cyclic_flag": true,
111
+ "add_method_conditioning": true,
112
+ "add_modified_flag": true,
113
+ "add_mol_type_feat": true,
114
+ "atom_encoder_depth": 3,
115
+ "atom_encoder_heads": 4
116
+ },
117
+ "exclude_ions_from_lddt": true,
118
+ "fix_sym_check": true,
119
+ "freeze_template_weights": false,
120
+ "guidance_args": null,
121
+ "ignore_ckpt_shape_mismatch": false,
122
+ "inference_logging": false,
123
+ "inverse_fold": false,
124
+ "inverse_fold_args": null,
125
+ "masker_args": {},
126
+ "max_dist": 22.0,
127
+ "maximum_bond_distance": 0,
128
+ "min_dist": 2.0,
129
+ "model_type": "boltzgen",
130
+ "msa_args": {
131
+ "activation_checkpointing": false,
132
+ "miniformer_blocks": false,
133
+ "msa_blocks": 4,
134
+ "msa_dropout": 0.15,
135
+ "msa_s": 64,
136
+ "pairwise_head_width": 32,
137
+ "pairwise_num_heads": 4,
138
+ "use_paired_feature": true,
139
+ "z_dropout": 0.25
140
+ },
141
+ "num_bins": 64,
142
+ "num_distograms": 1,
143
+ "num_tistogram_axis": 1,
144
+ "num_val_datasets": 4,
145
+ "pairformer_args": {
146
+ "activation_checkpointing": false,
147
+ "dropout": 0.25,
148
+ "num_blocks": 64,
149
+ "num_heads": 16,
150
+ "post_layer_norm": false
151
+ },
152
+ "predict_bfactor": true,
153
+ "predict_res_type": false,
154
+ "recycling_detach": true,
155
+ "refolding_validator": null,
156
+ "relative_confidence_supervision_weight": 0.0,
157
+ "representative_lddt": false,
158
+ "score_model_args": {
159
+ "activation_checkpointing": false,
160
+ "atom_decoder_depth": 3,
161
+ "atom_decoder_heads": 4,
162
+ "atom_encoder_depth": 3,
163
+ "atom_encoder_heads": 4,
164
+ "conditioning_transition_layers": 2,
165
+ "dim_fourier": 256,
166
+ "sigma_data": 16,
167
+ "token_transformer_depth": 24,
168
+ "token_transformer_heads": 16,
169
+ "transformer_post_ln": false
170
+ },
171
+ "skip_run_structure": false,
172
+ "structure_prediction_training": false,
173
+ "symmetry_correction_trunk": false,
174
+ "tau_affinity_score": -1.0,
175
+ "template_args": {
176
+ "activation_checkpointing": false,
177
+ "template_blocks": 2,
178
+ "template_dim": 64
179
+ },
180
+ "token_distance_args": null,
181
+ "token_level_confidence": true,
182
+ "token_s": 384,
183
+ "token_z": 128,
184
+ "training_args": {
185
+ "adam_beta_1": 0.9,
186
+ "adam_beta_2": 0.95,
187
+ "adam_eps": 1e-08,
188
+ "affinity_loss_weight": 0.003,
189
+ "base_lr": 0.0,
190
+ "bfactor_loss_weight": 0.001,
191
+ "confidence_loss_weight": 0.3,
192
+ "diffusion_loss_weight": 4.0,
193
+ "diffusion_multiplicity": 32,
194
+ "diffusion_samples": 1,
195
+ "distogram_loss_weight": 0.03,
196
+ "lr_decay_every_n_steps": 50000,
197
+ "lr_decay_factor": 0.95,
198
+ "lr_scheduler": "af3",
199
+ "lr_start_decay_after_n_steps": 50000,
200
+ "lr_warmup_no_steps": 1000,
201
+ "max_lr": 0.001,
202
+ "recycling_steps": 3,
203
+ "sampling_steps": 50,
204
+ "sampling_steps_random": [
205
+ 20,
206
+ 50,
207
+ 200
208
+ ],
209
+ "symmetry_correction": true,
210
+ "weight_decay": 0.003,
211
+ "weight_decay_exclude": true
212
+ },
213
+ "transformers_version": "4.57.1",
214
+ "trunk_resolved_loss": false,
215
+ "use_atom_backbone_feat": false,
216
+ "use_kernels": false,
217
+ "use_miniformer": false,
218
+ "use_miniformer_plus": false,
219
+ "use_no_atom_char": false,
220
+ "use_residue_feats_atoms": false,
221
+ "use_templates": true,
222
+ "use_templates_v2": true,
223
+ "use_token_distances": false,
224
+ "validation_args": {
225
+ "diffusion_samples": 5,
226
+ "recycling_steps": 3,
227
+ "run_confidence_sequentially": true,
228
+ "sampling_steps": 200,
229
+ "symmetry_correction": true
230
+ },
231
+ "validators": "[<__main__.DummyValidator object at 0x00000187A3DBD550>, <__main__.DummyValidator object at 0x00000187A5D718D0>, <__main__.DummyValidator object at 0x00000187A5F44350>, <__main__.DummyValidator object at 0x00000187A415B250>]"
232
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89b7a724d48b4d2ec9c633880242a1f20dbde00c4812a0e49b44709e4378d4c
3
+ size 2028676823