TTangenty commited on
Commit
2f5339e
·
verified ·
1 Parent(s): aa3b063

Add Dense FP32 E3 checkpoint at epoch 1.5 step 9375

Browse files
editmgt-e3-dense-fp32-epoch1.5-step9375/COMPLETED.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "architecture.json": "0856dbc457f15a2a064e40e799a02cfbade06a1796b7804b3305d1a53887dbe8",
4
+ "fingerprint.json": "df8ff56143ab49ab7d22ccf325759e515e73b975c7682403ff8f0ddc00e835b0",
5
+ "identity.json": "00301dd9fab7e7189237e9d920272b2c938ec2f1fceb39195d0517b938fcff77",
6
+ "metadata.json": "da9893898a31346eeee3e0cbebd52de851a61b8dfb12ce3c9a5e38b49296e729",
7
+ "model-00001.safetensors": "8529f622ee266c72c62089c09b41521dcaf0a9534e91100f7d93afd9454f733a",
8
+ "model-00002.safetensors": "03d6d48846373024f98f6215e7c70f6e7f90711f15c132cb8ff73f907deab3dc",
9
+ "model-00003.safetensors": "cd22ac77b19dc7fd44f97df8d48e7e51180780759c9ffcdb2c756e5e16700c96",
10
+ "model-00004.safetensors": "ca67b3de716e03f77216b64ab8859be9a16a7254d1b149310241bbd2197170de",
11
+ "model-00005.safetensors": "e05e4bd01039f778a998ca6c4b0db2cedbd25499112252f7e59579af781154bc",
12
+ "model-00006.safetensors": "e60d5c9088152e8cbe969d843fc94b4d06875c6444f575f7b9e2c6feb240e4df",
13
+ "model-00007.safetensors": "3dcd2a79b7f1e2d64ec71d6a90901aedbfdb46f3cf366944c2d6ea64337e1a1a",
14
+ "model-00008.safetensors": "3b44fec05c99670f7f1ba59ef914ce26f5cafe2c93c868ffdf5add730d1084fe",
15
+ "model.safetensors.index.json": "0710b7421a14af2dc71aa9c7ddd8ad7ee8ed9f597a423bfea86e9bb085b1854c",
16
+ "training_state.pt": "31470f48f62cecad480838783b614bc0028054d9e46db2849bc1ad965ec46e59"
17
+ },
18
+ "schema": "editmgt-dense-checkpoint-v1"
19
+ }
editmgt-e3-dense-fp32-epoch1.5-step9375/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ # editMGT Dense FP32 E3 — epoch 1.5 / step 9375
2
+
3
+ Full Transformer + region-conditioning checkpoint from the Dense E3 SFT experiment, saved at optimizer step9375 / 300000 sample exposures (1.5 epochs of frozen D200K). Global batch32 across8 GPUs, gradient accumulation4, LR2e-6, AdamW(0.9,0.95), BF16 forward autocast with FP32 trainable weights/gradients/moments. This is Dense E3 SFT; the DiMO checkpoints in other folders are different experiments.
4
+
5
+ - `model-*.safetensors` + `model.safetensors.index.json`: complete trained FP32 Transformer+region weights.
6
+ - `training_state.pt`: optimizer, scheduler, sampler cursor, quality state and per-rank RNG for strict resume.
7
+ - `COMPLETED.json`, `identity.json`, `fingerprint.json`, `architecture.json`, `metadata.json`: original atomic-checkpoint ledger and identity metadata, retained byte-for-byte.
8
+
9
+ Frozen text encoders, VQ model and datasets are not included. Use the matching released base components and the source repository's Dense loader; original fingerprint/path/resume identity checks apply. The source snapshot for this run is `exp/e3-dense-fp32-v1` with local commit `5b5bdbdb43711dc568b6e56274b4b9e1a1f2bc3a`. Corpus exhaustive auditing was skipped at the user's request and is labeled in the original fingerprint. This is an intermediate1.5epoch checkpoint while the5epoch SFT run continues; no final selected-teacher quality claim.
editmgt-e3-dense-fp32-epoch1.5-step9375/architecture.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_head_dim": 128,
3
+ "axes_dims_rope": [
4
+ 16,
5
+ 56,
6
+ 56
7
+ ],
8
+ "codebook_size": 8192,
9
+ "connector_type": "linear",
10
+ "downsample": true,
11
+ "guidance_embeds": false,
12
+ "in_channels": 64,
13
+ "joint_attention_dim": 2304,
14
+ "num_attention_heads": 8,
15
+ "num_layers": 14,
16
+ "num_single_layers": 28,
17
+ "patch_size": 1,
18
+ "pooled_projection_dim": 1024,
19
+ "text_encoder_architecture": "CLIP_Gemma2",
20
+ "upsample": true,
21
+ "vocab_size": 8256
22
+ }
editmgt-e3-dense-fp32-epoch1.5-step9375/fingerprint.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "payload": {
3
+ "attention_backend": "math_sdp",
4
+ "audit_status": "SKIPPED_BY_USER",
5
+ "component_dtypes": {
6
+ "text_encoders": "bf16",
7
+ "transformer": "fp32",
8
+ "vqvae": "fp32"
9
+ },
10
+ "corpus_schema": "fixed200k-ready-user-noaudit-v1",
11
+ "corruption": {
12
+ "full_roi_mask_probability": 0.15,
13
+ "mode": "roi_hardlock",
14
+ "persistent_conditioning": true,
15
+ "roi_probability": 1.0
16
+ },
17
+ "data": {
18
+ "corpus_ready": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/CORPUS_READY.json",
19
+ "manifest": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/train_200k.jsonl",
20
+ "metadata": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/train_200k.meta.json",
21
+ "name": "fixed_200k",
22
+ "roots": {
23
+ "crispedit": "/tmp/editmgt-tanyue-20261008/assets/datasets/crispedit",
24
+ "interedit": "/tmp/editmgt-tanyue-20261008/assets/datasets/interedit",
25
+ "magicbrush": "/tmp/editmgt-tanyue-20261008/assets/datasets/magicbrush/train",
26
+ "scaleedit": "/tmp/editmgt-tanyue-20261008/assets/datasets/scaleedit"
27
+ },
28
+ "translation": {
29
+ "backend": "nllb",
30
+ "decoding": {
31
+ "do_sample": false,
32
+ "max_new_tokens": 128,
33
+ "num_beams": 1
34
+ },
35
+ "immutable_revision": "7be3e24664b38ce1cac29b8aeed6911aa0cf0576",
36
+ "repo": "facebook/nllb-200-distilled-1.3B",
37
+ "src_lang": "zho_Hans",
38
+ "tgt_lang": "eng_Latn"
39
+ },
40
+ "translation_cache": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/translation_cache.jsonl",
41
+ "translation_config": "configs/translation/nllb.yaml",
42
+ "verify_hashes_at_read": true
43
+ },
44
+ "data_content_hashes": {
45
+ "data.corpus_ready": {
46
+ "resolved_path": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/CORPUS_READY.json",
47
+ "sha256": "f4c12f3c3d3d593691a746e94833a93ceb96036044b2fb664f7d7cdc798ed8ec"
48
+ },
49
+ "data.manifest": {
50
+ "resolved_path": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/train_200k.jsonl",
51
+ "sha256": "d4cd8c8776653bcac589c6df66c0fd0579fa7c26f9f53fd399a797943b2006ae"
52
+ },
53
+ "data.metadata": {
54
+ "resolved_path": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/train_200k.meta.json",
55
+ "sha256": "5135acd32721cddf8dc5d8f40456a16038f5a21e17a1a4ee4785afb67f75c00b"
56
+ },
57
+ "data.translation_cache": {
58
+ "resolved_path": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/translation_cache.jsonl",
59
+ "sha256": "cef0791f1c609a7aa21c51566ca61175816aa929aff12d285d6ed1bf8ed41ba0"
60
+ },
61
+ "data.translation_config": {
62
+ "resolved_path": "/opt/tiger/tanyue/editMGT-e3-dense-fp32/configs/translation/nllb.yaml",
63
+ "sha256": "3b039cea4c40bb14019360d836bbaaa67b6b200e53538d283e6bfe6712364de6"
64
+ },
65
+ "validation.manifest": {
66
+ "resolved_path": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/validation/magicbrush_probe128.jsonl",
67
+ "sha256": "63947c15f3b7254cad816afacd0af8800b02135b560941e24d33925824bcb0ac"
68
+ }
69
+ },
70
+ "dense": {
71
+ "allowed_unused_parameters": [],
72
+ "diagnostic_interval": 100,
73
+ "diagnostic_steps": [
74
+ 1,
75
+ 4,
76
+ 8,
77
+ 16
78
+ ],
79
+ "max_shard_bytes": 536870912,
80
+ "minimum_free_vram_gib": 38
81
+ },
82
+ "distributed_reduction": {
83
+ "nccl_algo": "Ring",
84
+ "nccl_proto": "Simple",
85
+ "resume_bucket_priming": true
86
+ },
87
+ "epochs": 5,
88
+ "git_dirty_diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
89
+ "git_sha": "5b5bdbdb43711dc568b6e56274b4b9e1a1f2bc3a",
90
+ "gradient_accumulation": 4,
91
+ "lora": {
92
+ "enabled": false
93
+ },
94
+ "loss": "per_sample_normalized_ce",
95
+ "max_optimizer_steps": 31250,
96
+ "model_identity": {
97
+ "components": {
98
+ "llm_encoder": {
99
+ "config_sha256": "eacec6c5ca317a87ed2c46789d9705b9274db5027e7ba59da739bfae23addb55"
100
+ },
101
+ "scheduler": {
102
+ "config_sha256": "de28f73f40d0834ac252ac65ef48dc35fcec8a3b50b52cd80d0bb7c99884bdb6"
103
+ },
104
+ "text_encoder": {
105
+ "config_sha256": "d891548c47c3c7770f3419af22093c7f98e76f6e5ec77fd444ef24ee76607aed"
106
+ },
107
+ "tokenizer": {
108
+ "config_sha256": "516314ccab66918d7cb647480ac27abd3520d14e1e5825aac99f50c851c16071"
109
+ },
110
+ "transformer": {
111
+ "config_sha256": "68effa13da0faa17b41dfcb754d81b7402044ff64d8ca9eb7f678d60263e2948"
112
+ },
113
+ "vqvae": {
114
+ "config_sha256": "f543c65e38300b098436a93d7b2c9e8246b47b3e9be8e0e6e37a5a5c6a050161"
115
+ }
116
+ },
117
+ "repo_id": "WeiChow/EditMGT",
118
+ "resolved_revision": "0a00f14ea159728fb76ac99ed741f9deca5fee28"
119
+ },
120
+ "model_snapshot": "0a00f14ea159728fb76ac99ed741f9deca5fee28",
121
+ "optimizer": {
122
+ "betas": [
123
+ 0.9,
124
+ 0.95
125
+ ],
126
+ "gradient_clip": 1.0,
127
+ "learning_rate": 2e-06,
128
+ "name": "AdamW",
129
+ "scheduler": "constant_with_warmup",
130
+ "weight_decay": 0.01
131
+ },
132
+ "per_device_batch": 1,
133
+ "precision": "bf16",
134
+ "released_weight_hashes": {
135
+ "diffusion_pytorch_model.safetensors": "fdea4a258e94a5e7efcee1691269e2764f74249808e566fe536b7abb766cd476"
136
+ },
137
+ "resolution": 1024,
138
+ "run_classification": "USER_REQUESTED_NOAUDIT_NOT_FULL_FORMAL_V3",
139
+ "sampler_schema": "fixed200k-hash-sort-v1",
140
+ "scheduler_horizon_steps": 31250,
141
+ "schema": "dense-e3-fp32-recipe-v1",
142
+ "seed": 42,
143
+ "token_mask": {
144
+ "coverage_threshold": 0.5,
145
+ "dilation_tokens": 0,
146
+ "minimum_edit_tokens": 1,
147
+ "mode": "any_overlap"
148
+ },
149
+ "torch_compile": false,
150
+ "training_mode": "full_transformer",
151
+ "user_audit_waiver_sha256": "4a205155cf2b76f9ed70d32a815b5e31afdc50896860bd665ed29bc0e21f8283",
152
+ "uv_lock_sha256": "01700b1b3d9daa3a66ce7f10d033916215681a9111c71d2a3b11433edf736d75",
153
+ "validation": {
154
+ "dataset_root": "/tmp/editmgt-tanyue-20261008/assets/datasets/magicbrush/dev",
155
+ "enabled": true,
156
+ "inference_config": "configs/eval/dense_periodic_probe.yaml",
157
+ "interval_steps": 3125,
158
+ "manifest": "/tmp/editmgt-tanyue-20261008/assets/derived/fixed200k/validation/magicbrush_probe128.jsonl",
159
+ "protocol": "fixed200k_magicbrush_probe"
160
+ },
161
+ "warmup_steps": 200,
162
+ "world_size": 8
163
+ },
164
+ "sha256": "1cf5ffb2afbe598dd1a49f1c11b17c796f47ef409f23489927c995074d44b9f0"
165
+ }
editmgt-e3-dense-fp32-epoch1.5-step9375/identity.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_sha256": "3d38297c9219a88848d866b26626ba80695bb617f5fde3bd2f0764bc1e7558c0",
3
+ "has_training_state": true,
4
+ "inference_files": {
5
+ "architecture.json": "0856dbc457f15a2a064e40e799a02cfbade06a1796b7804b3305d1a53887dbe8",
6
+ "fingerprint.json": "df8ff56143ab49ab7d22ccf325759e515e73b975c7682403ff8f0ddc00e835b0",
7
+ "metadata.json": "da9893898a31346eeee3e0cbebd52de851a61b8dfb12ce3c9a5e38b49296e729",
8
+ "model-00001.safetensors": "8529f622ee266c72c62089c09b41521dcaf0a9534e91100f7d93afd9454f733a",
9
+ "model-00002.safetensors": "03d6d48846373024f98f6215e7c70f6e7f90711f15c132cb8ff73f907deab3dc",
10
+ "model-00003.safetensors": "cd22ac77b19dc7fd44f97df8d48e7e51180780759c9ffcdb2c756e5e16700c96",
11
+ "model-00004.safetensors": "ca67b3de716e03f77216b64ab8859be9a16a7254d1b149310241bbd2197170de",
12
+ "model-00005.safetensors": "e05e4bd01039f778a998ca6c4b0db2cedbd25499112252f7e59579af781154bc",
13
+ "model-00006.safetensors": "e60d5c9088152e8cbe969d843fc94b4d06875c6444f575f7b9e2c6feb240e4df",
14
+ "model-00007.safetensors": "3dcd2a79b7f1e2d64ec71d6a90901aedbfdb46f3cf366944c2d6ea64337e1a1a",
15
+ "model-00008.safetensors": "3b44fec05c99670f7f1ba59ef914ce26f5cafe2c93c868ffdf5add730d1084fe",
16
+ "model.safetensors.index.json": "0710b7421a14af2dc71aa9c7ddd8ad7ee8ed9f597a423bfea86e9bb085b1854c"
17
+ },
18
+ "schema": "editmgt-dense-checkpoint-v1"
19
+ }
editmgt-e3-dense-fp32-epoch1.5-step9375/metadata.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "committed_global_sample_count": 300000,
3
+ "global_optimizer_step": 9375,
4
+ "sampler_state": {
5
+ "batch_per_gpu": 1,
6
+ "epoch": 1,
7
+ "epoch_ce_count": 100000,
8
+ "epoch_ce_sum": 565069.6711260099,
9
+ "epoch_permutation_sha256": "ebebd7db1781ddb92bbb0ff95612db33214a1ec01028684d199cc97d3daf073b",
10
+ "gradient_accumulation": 4,
11
+ "sampler_schema_version": "fixed200k-hash-sort-v1",
12
+ "samples_consumed_in_epoch": 100000,
13
+ "train_200k_sha256": "d4cd8c8776653bcac589c6df66c0fd0579fa7c26f9f53fd399a797943b2006ae",
14
+ "world_size": 8
15
+ },
16
+ "training_mode": "full_transformer",
17
+ "world_size": 8
18
+ }
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8529f622ee266c72c62089c09b41521dcaf0a9534e91100f7d93afd9454f733a
3
+ size 531210024
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d6d48846373024f98f6215e7c70f6e7f90711f15c132cb8ff73f907deab3dc
3
+ size 520479776
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd22ac77b19dc7fd44f97df8d48e7e51180780759c9ffcdb2c756e5e16700c96
3
+ size 533072568
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca67b3de716e03f77216b64ab8859be9a16a7254d1b149310241bbd2197170de
3
+ size 521570456
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05e4bd01039f778a998ca6c4b0db2cedbd25499112252f7e59579af781154bc
3
+ size 528938656
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60d5c9088152e8cbe969d843fc94b4d06875c6444f575f7b9e2c6feb240e4df
3
+ size 528926008
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dcd2a79b7f1e2d64ec71d6a90901aedbfdb46f3cf366944c2d6ea64337e1a1a
3
+ size 528938568
editmgt-e3-dense-fp32-epoch1.5-step9375/model-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b44fec05c99670f7f1ba59ef914ce26f5cafe2c93c868ffdf5add730d1084fe
3
+ size 344194448
editmgt-e3-dense-fp32-epoch1.5-step9375/model.safetensors.index.json ADDED
@@ -0,0 +1,874 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "cond_embed.linear_1.weight": "model-00001.safetensors",
4
+ "cond_embed.linear_2.weight": "model-00001.safetensors",
5
+ "connector.projector.bias": "model-00001.safetensors",
6
+ "connector.projector.weight": "model-00001.safetensors",
7
+ "context_embedder.bias": "model-00001.safetensors",
8
+ "context_embedder.weight": "model-00001.safetensors",
9
+ "down_block.downsample.conv.weight": "model-00001.safetensors",
10
+ "down_block.downsample.norm.weight": "model-00001.safetensors",
11
+ "edit_region_embedding": "model-00001.safetensors",
12
+ "embed.conv.weight": "model-00001.safetensors",
13
+ "embed.embeddings.weight": "model-00001.safetensors",
14
+ "embed.layer_norm.weight": "model-00001.safetensors",
15
+ "encoder_proj_layer_norm.weight": "model-00001.safetensors",
16
+ "mlm_layer.conv1.weight": "model-00001.safetensors",
17
+ "mlm_layer.conv2.weight": "model-00001.safetensors",
18
+ "mlm_layer.layer_norm.weight": "model-00001.safetensors",
19
+ "project_from_hidden.weight": "model-00001.safetensors",
20
+ "project_from_hidden_norm.weight": "model-00001.safetensors",
21
+ "project_to_hidden.weight": "model-00001.safetensors",
22
+ "project_to_hidden_norm.weight": "model-00001.safetensors",
23
+ "single_transformer_blocks.0.attn.norm_k.weight": "model-00001.safetensors",
24
+ "single_transformer_blocks.0.attn.norm_q.weight": "model-00001.safetensors",
25
+ "single_transformer_blocks.0.attn.to_k.bias": "model-00001.safetensors",
26
+ "single_transformer_blocks.0.attn.to_k.weight": "model-00001.safetensors",
27
+ "single_transformer_blocks.0.attn.to_q.bias": "model-00001.safetensors",
28
+ "single_transformer_blocks.0.attn.to_q.weight": "model-00001.safetensors",
29
+ "single_transformer_blocks.0.attn.to_v.bias": "model-00001.safetensors",
30
+ "single_transformer_blocks.0.attn.to_v.weight": "model-00001.safetensors",
31
+ "single_transformer_blocks.0.norm.linear.bias": "model-00001.safetensors",
32
+ "single_transformer_blocks.0.norm.linear.weight": "model-00001.safetensors",
33
+ "single_transformer_blocks.0.proj_mlp.bias": "model-00001.safetensors",
34
+ "single_transformer_blocks.0.proj_mlp.weight": "model-00001.safetensors",
35
+ "single_transformer_blocks.0.proj_out.bias": "model-00001.safetensors",
36
+ "single_transformer_blocks.0.proj_out.weight": "model-00001.safetensors",
37
+ "single_transformer_blocks.1.attn.norm_k.weight": "model-00001.safetensors",
38
+ "single_transformer_blocks.1.attn.norm_q.weight": "model-00001.safetensors",
39
+ "single_transformer_blocks.1.attn.to_k.bias": "model-00001.safetensors",
40
+ "single_transformer_blocks.1.attn.to_k.weight": "model-00001.safetensors",
41
+ "single_transformer_blocks.1.attn.to_q.bias": "model-00001.safetensors",
42
+ "single_transformer_blocks.1.attn.to_q.weight": "model-00001.safetensors",
43
+ "single_transformer_blocks.1.attn.to_v.bias": "model-00001.safetensors",
44
+ "single_transformer_blocks.1.attn.to_v.weight": "model-00001.safetensors",
45
+ "single_transformer_blocks.1.norm.linear.bias": "model-00001.safetensors",
46
+ "single_transformer_blocks.1.norm.linear.weight": "model-00001.safetensors",
47
+ "single_transformer_blocks.1.proj_mlp.bias": "model-00001.safetensors",
48
+ "single_transformer_blocks.1.proj_mlp.weight": "model-00001.safetensors",
49
+ "single_transformer_blocks.1.proj_out.bias": "model-00001.safetensors",
50
+ "single_transformer_blocks.1.proj_out.weight": "model-00001.safetensors",
51
+ "single_transformer_blocks.10.attn.norm_k.weight": "model-00001.safetensors",
52
+ "single_transformer_blocks.10.attn.norm_q.weight": "model-00001.safetensors",
53
+ "single_transformer_blocks.10.attn.to_k.bias": "model-00001.safetensors",
54
+ "single_transformer_blocks.10.attn.to_k.weight": "model-00001.safetensors",
55
+ "single_transformer_blocks.10.attn.to_q.bias": "model-00001.safetensors",
56
+ "single_transformer_blocks.10.attn.to_q.weight": "model-00001.safetensors",
57
+ "single_transformer_blocks.10.attn.to_v.bias": "model-00001.safetensors",
58
+ "single_transformer_blocks.10.attn.to_v.weight": "model-00001.safetensors",
59
+ "single_transformer_blocks.10.norm.linear.bias": "model-00001.safetensors",
60
+ "single_transformer_blocks.10.norm.linear.weight": "model-00001.safetensors",
61
+ "single_transformer_blocks.10.proj_mlp.bias": "model-00001.safetensors",
62
+ "single_transformer_blocks.10.proj_mlp.weight": "model-00001.safetensors",
63
+ "single_transformer_blocks.10.proj_out.bias": "model-00001.safetensors",
64
+ "single_transformer_blocks.10.proj_out.weight": "model-00001.safetensors",
65
+ "single_transformer_blocks.11.attn.norm_k.weight": "model-00001.safetensors",
66
+ "single_transformer_blocks.11.attn.norm_q.weight": "model-00001.safetensors",
67
+ "single_transformer_blocks.11.attn.to_k.bias": "model-00001.safetensors",
68
+ "single_transformer_blocks.11.attn.to_k.weight": "model-00001.safetensors",
69
+ "single_transformer_blocks.11.attn.to_q.bias": "model-00001.safetensors",
70
+ "single_transformer_blocks.11.attn.to_q.weight": "model-00001.safetensors",
71
+ "single_transformer_blocks.11.attn.to_v.bias": "model-00001.safetensors",
72
+ "single_transformer_blocks.11.attn.to_v.weight": "model-00001.safetensors",
73
+ "single_transformer_blocks.11.norm.linear.bias": "model-00001.safetensors",
74
+ "single_transformer_blocks.11.norm.linear.weight": "model-00001.safetensors",
75
+ "single_transformer_blocks.11.proj_mlp.bias": "model-00001.safetensors",
76
+ "single_transformer_blocks.11.proj_mlp.weight": "model-00001.safetensors",
77
+ "single_transformer_blocks.11.proj_out.bias": "model-00001.safetensors",
78
+ "single_transformer_blocks.11.proj_out.weight": "model-00001.safetensors",
79
+ "single_transformer_blocks.12.attn.norm_k.weight": "model-00001.safetensors",
80
+ "single_transformer_blocks.12.attn.norm_q.weight": "model-00001.safetensors",
81
+ "single_transformer_blocks.12.attn.to_k.bias": "model-00001.safetensors",
82
+ "single_transformer_blocks.12.attn.to_k.weight": "model-00001.safetensors",
83
+ "single_transformer_blocks.12.attn.to_q.bias": "model-00001.safetensors",
84
+ "single_transformer_blocks.12.attn.to_q.weight": "model-00001.safetensors",
85
+ "single_transformer_blocks.12.attn.to_v.bias": "model-00001.safetensors",
86
+ "single_transformer_blocks.12.attn.to_v.weight": "model-00001.safetensors",
87
+ "single_transformer_blocks.12.norm.linear.bias": "model-00001.safetensors",
88
+ "single_transformer_blocks.12.norm.linear.weight": "model-00001.safetensors",
89
+ "single_transformer_blocks.12.proj_mlp.bias": "model-00001.safetensors",
90
+ "single_transformer_blocks.12.proj_mlp.weight": "model-00001.safetensors",
91
+ "single_transformer_blocks.12.proj_out.bias": "model-00001.safetensors",
92
+ "single_transformer_blocks.12.proj_out.weight": "model-00001.safetensors",
93
+ "single_transformer_blocks.13.attn.norm_k.weight": "model-00001.safetensors",
94
+ "single_transformer_blocks.13.attn.norm_q.weight": "model-00001.safetensors",
95
+ "single_transformer_blocks.13.attn.to_k.bias": "model-00001.safetensors",
96
+ "single_transformer_blocks.13.attn.to_k.weight": "model-00001.safetensors",
97
+ "single_transformer_blocks.13.attn.to_q.bias": "model-00001.safetensors",
98
+ "single_transformer_blocks.13.attn.to_q.weight": "model-00001.safetensors",
99
+ "single_transformer_blocks.13.attn.to_v.bias": "model-00001.safetensors",
100
+ "single_transformer_blocks.13.attn.to_v.weight": "model-00001.safetensors",
101
+ "single_transformer_blocks.13.norm.linear.bias": "model-00001.safetensors",
102
+ "single_transformer_blocks.13.norm.linear.weight": "model-00001.safetensors",
103
+ "single_transformer_blocks.13.proj_mlp.bias": "model-00001.safetensors",
104
+ "single_transformer_blocks.13.proj_mlp.weight": "model-00001.safetensors",
105
+ "single_transformer_blocks.13.proj_out.bias": "model-00001.safetensors",
106
+ "single_transformer_blocks.13.proj_out.weight": "model-00001.safetensors",
107
+ "single_transformer_blocks.14.attn.norm_k.weight": "model-00001.safetensors",
108
+ "single_transformer_blocks.14.attn.norm_q.weight": "model-00001.safetensors",
109
+ "single_transformer_blocks.14.attn.to_k.bias": "model-00001.safetensors",
110
+ "single_transformer_blocks.14.attn.to_k.weight": "model-00001.safetensors",
111
+ "single_transformer_blocks.14.attn.to_q.bias": "model-00001.safetensors",
112
+ "single_transformer_blocks.14.attn.to_q.weight": "model-00001.safetensors",
113
+ "single_transformer_blocks.14.attn.to_v.bias": "model-00001.safetensors",
114
+ "single_transformer_blocks.14.attn.to_v.weight": "model-00001.safetensors",
115
+ "single_transformer_blocks.14.norm.linear.bias": "model-00001.safetensors",
116
+ "single_transformer_blocks.14.norm.linear.weight": "model-00001.safetensors",
117
+ "single_transformer_blocks.14.proj_mlp.bias": "model-00001.safetensors",
118
+ "single_transformer_blocks.14.proj_mlp.weight": "model-00002.safetensors",
119
+ "single_transformer_blocks.14.proj_out.bias": "model-00002.safetensors",
120
+ "single_transformer_blocks.14.proj_out.weight": "model-00002.safetensors",
121
+ "single_transformer_blocks.15.attn.norm_k.weight": "model-00002.safetensors",
122
+ "single_transformer_blocks.15.attn.norm_q.weight": "model-00002.safetensors",
123
+ "single_transformer_blocks.15.attn.to_k.bias": "model-00002.safetensors",
124
+ "single_transformer_blocks.15.attn.to_k.weight": "model-00002.safetensors",
125
+ "single_transformer_blocks.15.attn.to_q.bias": "model-00002.safetensors",
126
+ "single_transformer_blocks.15.attn.to_q.weight": "model-00002.safetensors",
127
+ "single_transformer_blocks.15.attn.to_v.bias": "model-00002.safetensors",
128
+ "single_transformer_blocks.15.attn.to_v.weight": "model-00002.safetensors",
129
+ "single_transformer_blocks.15.norm.linear.bias": "model-00002.safetensors",
130
+ "single_transformer_blocks.15.norm.linear.weight": "model-00002.safetensors",
131
+ "single_transformer_blocks.15.proj_mlp.bias": "model-00002.safetensors",
132
+ "single_transformer_blocks.15.proj_mlp.weight": "model-00002.safetensors",
133
+ "single_transformer_blocks.15.proj_out.bias": "model-00002.safetensors",
134
+ "single_transformer_blocks.15.proj_out.weight": "model-00002.safetensors",
135
+ "single_transformer_blocks.16.attn.norm_k.weight": "model-00002.safetensors",
136
+ "single_transformer_blocks.16.attn.norm_q.weight": "model-00002.safetensors",
137
+ "single_transformer_blocks.16.attn.to_k.bias": "model-00002.safetensors",
138
+ "single_transformer_blocks.16.attn.to_k.weight": "model-00002.safetensors",
139
+ "single_transformer_blocks.16.attn.to_q.bias": "model-00002.safetensors",
140
+ "single_transformer_blocks.16.attn.to_q.weight": "model-00002.safetensors",
141
+ "single_transformer_blocks.16.attn.to_v.bias": "model-00002.safetensors",
142
+ "single_transformer_blocks.16.attn.to_v.weight": "model-00002.safetensors",
143
+ "single_transformer_blocks.16.norm.linear.bias": "model-00002.safetensors",
144
+ "single_transformer_blocks.16.norm.linear.weight": "model-00002.safetensors",
145
+ "single_transformer_blocks.16.proj_mlp.bias": "model-00002.safetensors",
146
+ "single_transformer_blocks.16.proj_mlp.weight": "model-00002.safetensors",
147
+ "single_transformer_blocks.16.proj_out.bias": "model-00002.safetensors",
148
+ "single_transformer_blocks.16.proj_out.weight": "model-00002.safetensors",
149
+ "single_transformer_blocks.17.attn.norm_k.weight": "model-00002.safetensors",
150
+ "single_transformer_blocks.17.attn.norm_q.weight": "model-00002.safetensors",
151
+ "single_transformer_blocks.17.attn.to_k.bias": "model-00002.safetensors",
152
+ "single_transformer_blocks.17.attn.to_k.weight": "model-00002.safetensors",
153
+ "single_transformer_blocks.17.attn.to_q.bias": "model-00002.safetensors",
154
+ "single_transformer_blocks.17.attn.to_q.weight": "model-00002.safetensors",
155
+ "single_transformer_blocks.17.attn.to_v.bias": "model-00002.safetensors",
156
+ "single_transformer_blocks.17.attn.to_v.weight": "model-00002.safetensors",
157
+ "single_transformer_blocks.17.norm.linear.bias": "model-00002.safetensors",
158
+ "single_transformer_blocks.17.norm.linear.weight": "model-00002.safetensors",
159
+ "single_transformer_blocks.17.proj_mlp.bias": "model-00002.safetensors",
160
+ "single_transformer_blocks.17.proj_mlp.weight": "model-00002.safetensors",
161
+ "single_transformer_blocks.17.proj_out.bias": "model-00002.safetensors",
162
+ "single_transformer_blocks.17.proj_out.weight": "model-00002.safetensors",
163
+ "single_transformer_blocks.18.attn.norm_k.weight": "model-00002.safetensors",
164
+ "single_transformer_blocks.18.attn.norm_q.weight": "model-00002.safetensors",
165
+ "single_transformer_blocks.18.attn.to_k.bias": "model-00002.safetensors",
166
+ "single_transformer_blocks.18.attn.to_k.weight": "model-00002.safetensors",
167
+ "single_transformer_blocks.18.attn.to_q.bias": "model-00002.safetensors",
168
+ "single_transformer_blocks.18.attn.to_q.weight": "model-00002.safetensors",
169
+ "single_transformer_blocks.18.attn.to_v.bias": "model-00002.safetensors",
170
+ "single_transformer_blocks.18.attn.to_v.weight": "model-00002.safetensors",
171
+ "single_transformer_blocks.18.norm.linear.bias": "model-00002.safetensors",
172
+ "single_transformer_blocks.18.norm.linear.weight": "model-00002.safetensors",
173
+ "single_transformer_blocks.18.proj_mlp.bias": "model-00002.safetensors",
174
+ "single_transformer_blocks.18.proj_mlp.weight": "model-00002.safetensors",
175
+ "single_transformer_blocks.18.proj_out.bias": "model-00002.safetensors",
176
+ "single_transformer_blocks.18.proj_out.weight": "model-00002.safetensors",
177
+ "single_transformer_blocks.19.attn.norm_k.weight": "model-00002.safetensors",
178
+ "single_transformer_blocks.19.attn.norm_q.weight": "model-00002.safetensors",
179
+ "single_transformer_blocks.19.attn.to_k.bias": "model-00002.safetensors",
180
+ "single_transformer_blocks.19.attn.to_k.weight": "model-00002.safetensors",
181
+ "single_transformer_blocks.19.attn.to_q.bias": "model-00002.safetensors",
182
+ "single_transformer_blocks.19.attn.to_q.weight": "model-00002.safetensors",
183
+ "single_transformer_blocks.19.attn.to_v.bias": "model-00002.safetensors",
184
+ "single_transformer_blocks.19.attn.to_v.weight": "model-00002.safetensors",
185
+ "single_transformer_blocks.19.norm.linear.bias": "model-00002.safetensors",
186
+ "single_transformer_blocks.19.norm.linear.weight": "model-00002.safetensors",
187
+ "single_transformer_blocks.19.proj_mlp.bias": "model-00002.safetensors",
188
+ "single_transformer_blocks.19.proj_mlp.weight": "model-00002.safetensors",
189
+ "single_transformer_blocks.19.proj_out.bias": "model-00002.safetensors",
190
+ "single_transformer_blocks.19.proj_out.weight": "model-00002.safetensors",
191
+ "single_transformer_blocks.2.attn.norm_k.weight": "model-00002.safetensors",
192
+ "single_transformer_blocks.2.attn.norm_q.weight": "model-00002.safetensors",
193
+ "single_transformer_blocks.2.attn.to_k.bias": "model-00002.safetensors",
194
+ "single_transformer_blocks.2.attn.to_k.weight": "model-00002.safetensors",
195
+ "single_transformer_blocks.2.attn.to_q.bias": "model-00002.safetensors",
196
+ "single_transformer_blocks.2.attn.to_q.weight": "model-00002.safetensors",
197
+ "single_transformer_blocks.2.attn.to_v.bias": "model-00002.safetensors",
198
+ "single_transformer_blocks.2.attn.to_v.weight": "model-00002.safetensors",
199
+ "single_transformer_blocks.2.norm.linear.bias": "model-00002.safetensors",
200
+ "single_transformer_blocks.2.norm.linear.weight": "model-00002.safetensors",
201
+ "single_transformer_blocks.2.proj_mlp.bias": "model-00002.safetensors",
202
+ "single_transformer_blocks.2.proj_mlp.weight": "model-00002.safetensors",
203
+ "single_transformer_blocks.2.proj_out.bias": "model-00002.safetensors",
204
+ "single_transformer_blocks.2.proj_out.weight": "model-00002.safetensors",
205
+ "single_transformer_blocks.20.attn.norm_k.weight": "model-00002.safetensors",
206
+ "single_transformer_blocks.20.attn.norm_q.weight": "model-00002.safetensors",
207
+ "single_transformer_blocks.20.attn.to_k.bias": "model-00002.safetensors",
208
+ "single_transformer_blocks.20.attn.to_k.weight": "model-00002.safetensors",
209
+ "single_transformer_blocks.20.attn.to_q.bias": "model-00002.safetensors",
210
+ "single_transformer_blocks.20.attn.to_q.weight": "model-00002.safetensors",
211
+ "single_transformer_blocks.20.attn.to_v.bias": "model-00002.safetensors",
212
+ "single_transformer_blocks.20.attn.to_v.weight": "model-00002.safetensors",
213
+ "single_transformer_blocks.20.norm.linear.bias": "model-00002.safetensors",
214
+ "single_transformer_blocks.20.norm.linear.weight": "model-00002.safetensors",
215
+ "single_transformer_blocks.20.proj_mlp.bias": "model-00002.safetensors",
216
+ "single_transformer_blocks.20.proj_mlp.weight": "model-00002.safetensors",
217
+ "single_transformer_blocks.20.proj_out.bias": "model-00002.safetensors",
218
+ "single_transformer_blocks.20.proj_out.weight": "model-00002.safetensors",
219
+ "single_transformer_blocks.21.attn.norm_k.weight": "model-00002.safetensors",
220
+ "single_transformer_blocks.21.attn.norm_q.weight": "model-00002.safetensors",
221
+ "single_transformer_blocks.21.attn.to_k.bias": "model-00002.safetensors",
222
+ "single_transformer_blocks.21.attn.to_k.weight": "model-00002.safetensors",
223
+ "single_transformer_blocks.21.attn.to_q.bias": "model-00002.safetensors",
224
+ "single_transformer_blocks.21.attn.to_q.weight": "model-00002.safetensors",
225
+ "single_transformer_blocks.21.attn.to_v.bias": "model-00002.safetensors",
226
+ "single_transformer_blocks.21.attn.to_v.weight": "model-00002.safetensors",
227
+ "single_transformer_blocks.21.norm.linear.bias": "model-00002.safetensors",
228
+ "single_transformer_blocks.21.norm.linear.weight": "model-00002.safetensors",
229
+ "single_transformer_blocks.21.proj_mlp.bias": "model-00002.safetensors",
230
+ "single_transformer_blocks.21.proj_mlp.weight": "model-00002.safetensors",
231
+ "single_transformer_blocks.21.proj_out.bias": "model-00002.safetensors",
232
+ "single_transformer_blocks.21.proj_out.weight": "model-00003.safetensors",
233
+ "single_transformer_blocks.22.attn.norm_k.weight": "model-00003.safetensors",
234
+ "single_transformer_blocks.22.attn.norm_q.weight": "model-00003.safetensors",
235
+ "single_transformer_blocks.22.attn.to_k.bias": "model-00003.safetensors",
236
+ "single_transformer_blocks.22.attn.to_k.weight": "model-00003.safetensors",
237
+ "single_transformer_blocks.22.attn.to_q.bias": "model-00003.safetensors",
238
+ "single_transformer_blocks.22.attn.to_q.weight": "model-00003.safetensors",
239
+ "single_transformer_blocks.22.attn.to_v.bias": "model-00003.safetensors",
240
+ "single_transformer_blocks.22.attn.to_v.weight": "model-00003.safetensors",
241
+ "single_transformer_blocks.22.norm.linear.bias": "model-00003.safetensors",
242
+ "single_transformer_blocks.22.norm.linear.weight": "model-00003.safetensors",
243
+ "single_transformer_blocks.22.proj_mlp.bias": "model-00003.safetensors",
244
+ "single_transformer_blocks.22.proj_mlp.weight": "model-00003.safetensors",
245
+ "single_transformer_blocks.22.proj_out.bias": "model-00003.safetensors",
246
+ "single_transformer_blocks.22.proj_out.weight": "model-00003.safetensors",
247
+ "single_transformer_blocks.23.attn.norm_k.weight": "model-00003.safetensors",
248
+ "single_transformer_blocks.23.attn.norm_q.weight": "model-00003.safetensors",
249
+ "single_transformer_blocks.23.attn.to_k.bias": "model-00003.safetensors",
250
+ "single_transformer_blocks.23.attn.to_k.weight": "model-00003.safetensors",
251
+ "single_transformer_blocks.23.attn.to_q.bias": "model-00003.safetensors",
252
+ "single_transformer_blocks.23.attn.to_q.weight": "model-00003.safetensors",
253
+ "single_transformer_blocks.23.attn.to_v.bias": "model-00003.safetensors",
254
+ "single_transformer_blocks.23.attn.to_v.weight": "model-00003.safetensors",
255
+ "single_transformer_blocks.23.norm.linear.bias": "model-00003.safetensors",
256
+ "single_transformer_blocks.23.norm.linear.weight": "model-00003.safetensors",
257
+ "single_transformer_blocks.23.proj_mlp.bias": "model-00003.safetensors",
258
+ "single_transformer_blocks.23.proj_mlp.weight": "model-00003.safetensors",
259
+ "single_transformer_blocks.23.proj_out.bias": "model-00003.safetensors",
260
+ "single_transformer_blocks.23.proj_out.weight": "model-00003.safetensors",
261
+ "single_transformer_blocks.24.attn.norm_k.weight": "model-00003.safetensors",
262
+ "single_transformer_blocks.24.attn.norm_q.weight": "model-00003.safetensors",
263
+ "single_transformer_blocks.24.attn.to_k.bias": "model-00003.safetensors",
264
+ "single_transformer_blocks.24.attn.to_k.weight": "model-00003.safetensors",
265
+ "single_transformer_blocks.24.attn.to_q.bias": "model-00003.safetensors",
266
+ "single_transformer_blocks.24.attn.to_q.weight": "model-00003.safetensors",
267
+ "single_transformer_blocks.24.attn.to_v.bias": "model-00003.safetensors",
268
+ "single_transformer_blocks.24.attn.to_v.weight": "model-00003.safetensors",
269
+ "single_transformer_blocks.24.norm.linear.bias": "model-00003.safetensors",
270
+ "single_transformer_blocks.24.norm.linear.weight": "model-00003.safetensors",
271
+ "single_transformer_blocks.24.proj_mlp.bias": "model-00003.safetensors",
272
+ "single_transformer_blocks.24.proj_mlp.weight": "model-00003.safetensors",
273
+ "single_transformer_blocks.24.proj_out.bias": "model-00003.safetensors",
274
+ "single_transformer_blocks.24.proj_out.weight": "model-00003.safetensors",
275
+ "single_transformer_blocks.25.attn.norm_k.weight": "model-00003.safetensors",
276
+ "single_transformer_blocks.25.attn.norm_q.weight": "model-00003.safetensors",
277
+ "single_transformer_blocks.25.attn.to_k.bias": "model-00003.safetensors",
278
+ "single_transformer_blocks.25.attn.to_k.weight": "model-00003.safetensors",
279
+ "single_transformer_blocks.25.attn.to_q.bias": "model-00003.safetensors",
280
+ "single_transformer_blocks.25.attn.to_q.weight": "model-00003.safetensors",
281
+ "single_transformer_blocks.25.attn.to_v.bias": "model-00003.safetensors",
282
+ "single_transformer_blocks.25.attn.to_v.weight": "model-00003.safetensors",
283
+ "single_transformer_blocks.25.norm.linear.bias": "model-00003.safetensors",
284
+ "single_transformer_blocks.25.norm.linear.weight": "model-00003.safetensors",
285
+ "single_transformer_blocks.25.proj_mlp.bias": "model-00003.safetensors",
286
+ "single_transformer_blocks.25.proj_mlp.weight": "model-00003.safetensors",
287
+ "single_transformer_blocks.25.proj_out.bias": "model-00003.safetensors",
288
+ "single_transformer_blocks.25.proj_out.weight": "model-00003.safetensors",
289
+ "single_transformer_blocks.26.attn.norm_k.weight": "model-00003.safetensors",
290
+ "single_transformer_blocks.26.attn.norm_q.weight": "model-00003.safetensors",
291
+ "single_transformer_blocks.26.attn.to_k.bias": "model-00003.safetensors",
292
+ "single_transformer_blocks.26.attn.to_k.weight": "model-00003.safetensors",
293
+ "single_transformer_blocks.26.attn.to_q.bias": "model-00003.safetensors",
294
+ "single_transformer_blocks.26.attn.to_q.weight": "model-00003.safetensors",
295
+ "single_transformer_blocks.26.attn.to_v.bias": "model-00003.safetensors",
296
+ "single_transformer_blocks.26.attn.to_v.weight": "model-00003.safetensors",
297
+ "single_transformer_blocks.26.norm.linear.bias": "model-00003.safetensors",
298
+ "single_transformer_blocks.26.norm.linear.weight": "model-00003.safetensors",
299
+ "single_transformer_blocks.26.proj_mlp.bias": "model-00003.safetensors",
300
+ "single_transformer_blocks.26.proj_mlp.weight": "model-00003.safetensors",
301
+ "single_transformer_blocks.26.proj_out.bias": "model-00003.safetensors",
302
+ "single_transformer_blocks.26.proj_out.weight": "model-00003.safetensors",
303
+ "single_transformer_blocks.27.attn.norm_k.weight": "model-00003.safetensors",
304
+ "single_transformer_blocks.27.attn.norm_q.weight": "model-00003.safetensors",
305
+ "single_transformer_blocks.27.attn.to_k.bias": "model-00003.safetensors",
306
+ "single_transformer_blocks.27.attn.to_k.weight": "model-00003.safetensors",
307
+ "single_transformer_blocks.27.attn.to_q.bias": "model-00003.safetensors",
308
+ "single_transformer_blocks.27.attn.to_q.weight": "model-00003.safetensors",
309
+ "single_transformer_blocks.27.attn.to_v.bias": "model-00003.safetensors",
310
+ "single_transformer_blocks.27.attn.to_v.weight": "model-00003.safetensors",
311
+ "single_transformer_blocks.27.norm.linear.bias": "model-00003.safetensors",
312
+ "single_transformer_blocks.27.norm.linear.weight": "model-00003.safetensors",
313
+ "single_transformer_blocks.27.proj_mlp.bias": "model-00003.safetensors",
314
+ "single_transformer_blocks.27.proj_mlp.weight": "model-00003.safetensors",
315
+ "single_transformer_blocks.27.proj_out.bias": "model-00003.safetensors",
316
+ "single_transformer_blocks.27.proj_out.weight": "model-00003.safetensors",
317
+ "single_transformer_blocks.3.attn.norm_k.weight": "model-00003.safetensors",
318
+ "single_transformer_blocks.3.attn.norm_q.weight": "model-00003.safetensors",
319
+ "single_transformer_blocks.3.attn.to_k.bias": "model-00003.safetensors",
320
+ "single_transformer_blocks.3.attn.to_k.weight": "model-00003.safetensors",
321
+ "single_transformer_blocks.3.attn.to_q.bias": "model-00003.safetensors",
322
+ "single_transformer_blocks.3.attn.to_q.weight": "model-00003.safetensors",
323
+ "single_transformer_blocks.3.attn.to_v.bias": "model-00003.safetensors",
324
+ "single_transformer_blocks.3.attn.to_v.weight": "model-00003.safetensors",
325
+ "single_transformer_blocks.3.norm.linear.bias": "model-00003.safetensors",
326
+ "single_transformer_blocks.3.norm.linear.weight": "model-00003.safetensors",
327
+ "single_transformer_blocks.3.proj_mlp.bias": "model-00003.safetensors",
328
+ "single_transformer_blocks.3.proj_mlp.weight": "model-00003.safetensors",
329
+ "single_transformer_blocks.3.proj_out.bias": "model-00003.safetensors",
330
+ "single_transformer_blocks.3.proj_out.weight": "model-00003.safetensors",
331
+ "single_transformer_blocks.4.attn.norm_k.weight": "model-00003.safetensors",
332
+ "single_transformer_blocks.4.attn.norm_q.weight": "model-00003.safetensors",
333
+ "single_transformer_blocks.4.attn.to_k.bias": "model-00003.safetensors",
334
+ "single_transformer_blocks.4.attn.to_k.weight": "model-00003.safetensors",
335
+ "single_transformer_blocks.4.attn.to_q.bias": "model-00003.safetensors",
336
+ "single_transformer_blocks.4.attn.to_q.weight": "model-00003.safetensors",
337
+ "single_transformer_blocks.4.attn.to_v.bias": "model-00003.safetensors",
338
+ "single_transformer_blocks.4.attn.to_v.weight": "model-00003.safetensors",
339
+ "single_transformer_blocks.4.norm.linear.bias": "model-00003.safetensors",
340
+ "single_transformer_blocks.4.norm.linear.weight": "model-00003.safetensors",
341
+ "single_transformer_blocks.4.proj_mlp.bias": "model-00003.safetensors",
342
+ "single_transformer_blocks.4.proj_mlp.weight": "model-00003.safetensors",
343
+ "single_transformer_blocks.4.proj_out.bias": "model-00003.safetensors",
344
+ "single_transformer_blocks.4.proj_out.weight": "model-00003.safetensors",
345
+ "single_transformer_blocks.5.attn.norm_k.weight": "model-00003.safetensors",
346
+ "single_transformer_blocks.5.attn.norm_q.weight": "model-00003.safetensors",
347
+ "single_transformer_blocks.5.attn.to_k.bias": "model-00003.safetensors",
348
+ "single_transformer_blocks.5.attn.to_k.weight": "model-00003.safetensors",
349
+ "single_transformer_blocks.5.attn.to_q.bias": "model-00003.safetensors",
350
+ "single_transformer_blocks.5.attn.to_q.weight": "model-00003.safetensors",
351
+ "single_transformer_blocks.5.attn.to_v.bias": "model-00003.safetensors",
352
+ "single_transformer_blocks.5.attn.to_v.weight": "model-00004.safetensors",
353
+ "single_transformer_blocks.5.norm.linear.bias": "model-00004.safetensors",
354
+ "single_transformer_blocks.5.norm.linear.weight": "model-00004.safetensors",
355
+ "single_transformer_blocks.5.proj_mlp.bias": "model-00004.safetensors",
356
+ "single_transformer_blocks.5.proj_mlp.weight": "model-00004.safetensors",
357
+ "single_transformer_blocks.5.proj_out.bias": "model-00004.safetensors",
358
+ "single_transformer_blocks.5.proj_out.weight": "model-00004.safetensors",
359
+ "single_transformer_blocks.6.attn.norm_k.weight": "model-00004.safetensors",
360
+ "single_transformer_blocks.6.attn.norm_q.weight": "model-00004.safetensors",
361
+ "single_transformer_blocks.6.attn.to_k.bias": "model-00004.safetensors",
362
+ "single_transformer_blocks.6.attn.to_k.weight": "model-00004.safetensors",
363
+ "single_transformer_blocks.6.attn.to_q.bias": "model-00004.safetensors",
364
+ "single_transformer_blocks.6.attn.to_q.weight": "model-00004.safetensors",
365
+ "single_transformer_blocks.6.attn.to_v.bias": "model-00004.safetensors",
366
+ "single_transformer_blocks.6.attn.to_v.weight": "model-00004.safetensors",
367
+ "single_transformer_blocks.6.norm.linear.bias": "model-00004.safetensors",
368
+ "single_transformer_blocks.6.norm.linear.weight": "model-00004.safetensors",
369
+ "single_transformer_blocks.6.proj_mlp.bias": "model-00004.safetensors",
370
+ "single_transformer_blocks.6.proj_mlp.weight": "model-00004.safetensors",
371
+ "single_transformer_blocks.6.proj_out.bias": "model-00004.safetensors",
372
+ "single_transformer_blocks.6.proj_out.weight": "model-00004.safetensors",
373
+ "single_transformer_blocks.7.attn.norm_k.weight": "model-00004.safetensors",
374
+ "single_transformer_blocks.7.attn.norm_q.weight": "model-00004.safetensors",
375
+ "single_transformer_blocks.7.attn.to_k.bias": "model-00004.safetensors",
376
+ "single_transformer_blocks.7.attn.to_k.weight": "model-00004.safetensors",
377
+ "single_transformer_blocks.7.attn.to_q.bias": "model-00004.safetensors",
378
+ "single_transformer_blocks.7.attn.to_q.weight": "model-00004.safetensors",
379
+ "single_transformer_blocks.7.attn.to_v.bias": "model-00004.safetensors",
380
+ "single_transformer_blocks.7.attn.to_v.weight": "model-00004.safetensors",
381
+ "single_transformer_blocks.7.norm.linear.bias": "model-00004.safetensors",
382
+ "single_transformer_blocks.7.norm.linear.weight": "model-00004.safetensors",
383
+ "single_transformer_blocks.7.proj_mlp.bias": "model-00004.safetensors",
384
+ "single_transformer_blocks.7.proj_mlp.weight": "model-00004.safetensors",
385
+ "single_transformer_blocks.7.proj_out.bias": "model-00004.safetensors",
386
+ "single_transformer_blocks.7.proj_out.weight": "model-00004.safetensors",
387
+ "single_transformer_blocks.8.attn.norm_k.weight": "model-00004.safetensors",
388
+ "single_transformer_blocks.8.attn.norm_q.weight": "model-00004.safetensors",
389
+ "single_transformer_blocks.8.attn.to_k.bias": "model-00004.safetensors",
390
+ "single_transformer_blocks.8.attn.to_k.weight": "model-00004.safetensors",
391
+ "single_transformer_blocks.8.attn.to_q.bias": "model-00004.safetensors",
392
+ "single_transformer_blocks.8.attn.to_q.weight": "model-00004.safetensors",
393
+ "single_transformer_blocks.8.attn.to_v.bias": "model-00004.safetensors",
394
+ "single_transformer_blocks.8.attn.to_v.weight": "model-00004.safetensors",
395
+ "single_transformer_blocks.8.norm.linear.bias": "model-00004.safetensors",
396
+ "single_transformer_blocks.8.norm.linear.weight": "model-00004.safetensors",
397
+ "single_transformer_blocks.8.proj_mlp.bias": "model-00004.safetensors",
398
+ "single_transformer_blocks.8.proj_mlp.weight": "model-00004.safetensors",
399
+ "single_transformer_blocks.8.proj_out.bias": "model-00004.safetensors",
400
+ "single_transformer_blocks.8.proj_out.weight": "model-00004.safetensors",
401
+ "single_transformer_blocks.9.attn.norm_k.weight": "model-00004.safetensors",
402
+ "single_transformer_blocks.9.attn.norm_q.weight": "model-00004.safetensors",
403
+ "single_transformer_blocks.9.attn.to_k.bias": "model-00004.safetensors",
404
+ "single_transformer_blocks.9.attn.to_k.weight": "model-00004.safetensors",
405
+ "single_transformer_blocks.9.attn.to_q.bias": "model-00004.safetensors",
406
+ "single_transformer_blocks.9.attn.to_q.weight": "model-00004.safetensors",
407
+ "single_transformer_blocks.9.attn.to_v.bias": "model-00004.safetensors",
408
+ "single_transformer_blocks.9.attn.to_v.weight": "model-00004.safetensors",
409
+ "single_transformer_blocks.9.norm.linear.bias": "model-00004.safetensors",
410
+ "single_transformer_blocks.9.norm.linear.weight": "model-00004.safetensors",
411
+ "single_transformer_blocks.9.proj_mlp.bias": "model-00004.safetensors",
412
+ "single_transformer_blocks.9.proj_mlp.weight": "model-00004.safetensors",
413
+ "single_transformer_blocks.9.proj_out.bias": "model-00004.safetensors",
414
+ "single_transformer_blocks.9.proj_out.weight": "model-00004.safetensors",
415
+ "time_text_embed.text_embedder.linear_1.bias": "model-00004.safetensors",
416
+ "time_text_embed.text_embedder.linear_1.weight": "model-00004.safetensors",
417
+ "time_text_embed.text_embedder.linear_2.bias": "model-00004.safetensors",
418
+ "time_text_embed.text_embedder.linear_2.weight": "model-00004.safetensors",
419
+ "time_text_embed.timestep_embedder.linear_1.bias": "model-00004.safetensors",
420
+ "time_text_embed.timestep_embedder.linear_1.weight": "model-00004.safetensors",
421
+ "time_text_embed.timestep_embedder.linear_2.bias": "model-00004.safetensors",
422
+ "time_text_embed.timestep_embedder.linear_2.weight": "model-00004.safetensors",
423
+ "transformer_blocks.0.attn.add_k_proj.bias": "model-00004.safetensors",
424
+ "transformer_blocks.0.attn.add_k_proj.weight": "model-00004.safetensors",
425
+ "transformer_blocks.0.attn.add_q_proj.bias": "model-00004.safetensors",
426
+ "transformer_blocks.0.attn.add_q_proj.weight": "model-00004.safetensors",
427
+ "transformer_blocks.0.attn.add_v_proj.bias": "model-00004.safetensors",
428
+ "transformer_blocks.0.attn.add_v_proj.weight": "model-00004.safetensors",
429
+ "transformer_blocks.0.attn.norm_added_k.weight": "model-00004.safetensors",
430
+ "transformer_blocks.0.attn.norm_added_q.weight": "model-00004.safetensors",
431
+ "transformer_blocks.0.attn.norm_k.weight": "model-00004.safetensors",
432
+ "transformer_blocks.0.attn.norm_q.weight": "model-00004.safetensors",
433
+ "transformer_blocks.0.attn.to_add_out.bias": "model-00004.safetensors",
434
+ "transformer_blocks.0.attn.to_add_out.weight": "model-00004.safetensors",
435
+ "transformer_blocks.0.attn.to_k.bias": "model-00004.safetensors",
436
+ "transformer_blocks.0.attn.to_k.weight": "model-00004.safetensors",
437
+ "transformer_blocks.0.attn.to_out.0.bias": "model-00004.safetensors",
438
+ "transformer_blocks.0.attn.to_out.0.weight": "model-00004.safetensors",
439
+ "transformer_blocks.0.attn.to_q.bias": "model-00004.safetensors",
440
+ "transformer_blocks.0.attn.to_q.weight": "model-00004.safetensors",
441
+ "transformer_blocks.0.attn.to_v.bias": "model-00004.safetensors",
442
+ "transformer_blocks.0.attn.to_v.weight": "model-00004.safetensors",
443
+ "transformer_blocks.0.ff.net.0.proj.bias": "model-00004.safetensors",
444
+ "transformer_blocks.0.ff.net.0.proj.weight": "model-00004.safetensors",
445
+ "transformer_blocks.0.ff.net.2.bias": "model-00004.safetensors",
446
+ "transformer_blocks.0.ff.net.2.weight": "model-00004.safetensors",
447
+ "transformer_blocks.0.ff_context.net.0.proj.bias": "model-00004.safetensors",
448
+ "transformer_blocks.0.ff_context.net.0.proj.weight": "model-00004.safetensors",
449
+ "transformer_blocks.0.ff_context.net.2.bias": "model-00004.safetensors",
450
+ "transformer_blocks.0.ff_context.net.2.weight": "model-00004.safetensors",
451
+ "transformer_blocks.0.norm1.linear.bias": "model-00004.safetensors",
452
+ "transformer_blocks.0.norm1.linear.weight": "model-00004.safetensors",
453
+ "transformer_blocks.0.norm1_context.linear.bias": "model-00004.safetensors",
454
+ "transformer_blocks.0.norm1_context.linear.weight": "model-00004.safetensors",
455
+ "transformer_blocks.1.attn.add_k_proj.bias": "model-00004.safetensors",
456
+ "transformer_blocks.1.attn.add_k_proj.weight": "model-00004.safetensors",
457
+ "transformer_blocks.1.attn.add_q_proj.bias": "model-00004.safetensors",
458
+ "transformer_blocks.1.attn.add_q_proj.weight": "model-00004.safetensors",
459
+ "transformer_blocks.1.attn.add_v_proj.bias": "model-00004.safetensors",
460
+ "transformer_blocks.1.attn.add_v_proj.weight": "model-00004.safetensors",
461
+ "transformer_blocks.1.attn.norm_added_k.weight": "model-00004.safetensors",
462
+ "transformer_blocks.1.attn.norm_added_q.weight": "model-00004.safetensors",
463
+ "transformer_blocks.1.attn.norm_k.weight": "model-00004.safetensors",
464
+ "transformer_blocks.1.attn.norm_q.weight": "model-00004.safetensors",
465
+ "transformer_blocks.1.attn.to_add_out.bias": "model-00004.safetensors",
466
+ "transformer_blocks.1.attn.to_add_out.weight": "model-00004.safetensors",
467
+ "transformer_blocks.1.attn.to_k.bias": "model-00004.safetensors",
468
+ "transformer_blocks.1.attn.to_k.weight": "model-00004.safetensors",
469
+ "transformer_blocks.1.attn.to_out.0.bias": "model-00004.safetensors",
470
+ "transformer_blocks.1.attn.to_out.0.weight": "model-00004.safetensors",
471
+ "transformer_blocks.1.attn.to_q.bias": "model-00004.safetensors",
472
+ "transformer_blocks.1.attn.to_q.weight": "model-00004.safetensors",
473
+ "transformer_blocks.1.attn.to_v.bias": "model-00004.safetensors",
474
+ "transformer_blocks.1.attn.to_v.weight": "model-00004.safetensors",
475
+ "transformer_blocks.1.ff.net.0.proj.bias": "model-00004.safetensors",
476
+ "transformer_blocks.1.ff.net.0.proj.weight": "model-00004.safetensors",
477
+ "transformer_blocks.1.ff.net.2.bias": "model-00004.safetensors",
478
+ "transformer_blocks.1.ff.net.2.weight": "model-00005.safetensors",
479
+ "transformer_blocks.1.ff_context.net.0.proj.bias": "model-00005.safetensors",
480
+ "transformer_blocks.1.ff_context.net.0.proj.weight": "model-00005.safetensors",
481
+ "transformer_blocks.1.ff_context.net.2.bias": "model-00005.safetensors",
482
+ "transformer_blocks.1.ff_context.net.2.weight": "model-00005.safetensors",
483
+ "transformer_blocks.1.norm1.linear.bias": "model-00005.safetensors",
484
+ "transformer_blocks.1.norm1.linear.weight": "model-00005.safetensors",
485
+ "transformer_blocks.1.norm1_context.linear.bias": "model-00005.safetensors",
486
+ "transformer_blocks.1.norm1_context.linear.weight": "model-00005.safetensors",
487
+ "transformer_blocks.10.attn.add_k_proj.bias": "model-00005.safetensors",
488
+ "transformer_blocks.10.attn.add_k_proj.weight": "model-00005.safetensors",
489
+ "transformer_blocks.10.attn.add_q_proj.bias": "model-00005.safetensors",
490
+ "transformer_blocks.10.attn.add_q_proj.weight": "model-00005.safetensors",
491
+ "transformer_blocks.10.attn.add_v_proj.bias": "model-00005.safetensors",
492
+ "transformer_blocks.10.attn.add_v_proj.weight": "model-00005.safetensors",
493
+ "transformer_blocks.10.attn.norm_added_k.weight": "model-00005.safetensors",
494
+ "transformer_blocks.10.attn.norm_added_q.weight": "model-00005.safetensors",
495
+ "transformer_blocks.10.attn.norm_k.weight": "model-00005.safetensors",
496
+ "transformer_blocks.10.attn.norm_q.weight": "model-00005.safetensors",
497
+ "transformer_blocks.10.attn.to_add_out.bias": "model-00005.safetensors",
498
+ "transformer_blocks.10.attn.to_add_out.weight": "model-00005.safetensors",
499
+ "transformer_blocks.10.attn.to_k.bias": "model-00005.safetensors",
500
+ "transformer_blocks.10.attn.to_k.weight": "model-00005.safetensors",
501
+ "transformer_blocks.10.attn.to_out.0.bias": "model-00005.safetensors",
502
+ "transformer_blocks.10.attn.to_out.0.weight": "model-00005.safetensors",
503
+ "transformer_blocks.10.attn.to_q.bias": "model-00005.safetensors",
504
+ "transformer_blocks.10.attn.to_q.weight": "model-00005.safetensors",
505
+ "transformer_blocks.10.attn.to_v.bias": "model-00005.safetensors",
506
+ "transformer_blocks.10.attn.to_v.weight": "model-00005.safetensors",
507
+ "transformer_blocks.10.ff.net.0.proj.bias": "model-00005.safetensors",
508
+ "transformer_blocks.10.ff.net.0.proj.weight": "model-00005.safetensors",
509
+ "transformer_blocks.10.ff.net.2.bias": "model-00005.safetensors",
510
+ "transformer_blocks.10.ff.net.2.weight": "model-00005.safetensors",
511
+ "transformer_blocks.10.ff_context.net.0.proj.bias": "model-00005.safetensors",
512
+ "transformer_blocks.10.ff_context.net.0.proj.weight": "model-00005.safetensors",
513
+ "transformer_blocks.10.ff_context.net.2.bias": "model-00005.safetensors",
514
+ "transformer_blocks.10.ff_context.net.2.weight": "model-00005.safetensors",
515
+ "transformer_blocks.10.norm1.linear.bias": "model-00005.safetensors",
516
+ "transformer_blocks.10.norm1.linear.weight": "model-00005.safetensors",
517
+ "transformer_blocks.10.norm1_context.linear.bias": "model-00005.safetensors",
518
+ "transformer_blocks.10.norm1_context.linear.weight": "model-00005.safetensors",
519
+ "transformer_blocks.11.attn.add_k_proj.bias": "model-00005.safetensors",
520
+ "transformer_blocks.11.attn.add_k_proj.weight": "model-00005.safetensors",
521
+ "transformer_blocks.11.attn.add_q_proj.bias": "model-00005.safetensors",
522
+ "transformer_blocks.11.attn.add_q_proj.weight": "model-00005.safetensors",
523
+ "transformer_blocks.11.attn.add_v_proj.bias": "model-00005.safetensors",
524
+ "transformer_blocks.11.attn.add_v_proj.weight": "model-00005.safetensors",
525
+ "transformer_blocks.11.attn.norm_added_k.weight": "model-00005.safetensors",
526
+ "transformer_blocks.11.attn.norm_added_q.weight": "model-00005.safetensors",
527
+ "transformer_blocks.11.attn.norm_k.weight": "model-00005.safetensors",
528
+ "transformer_blocks.11.attn.norm_q.weight": "model-00005.safetensors",
529
+ "transformer_blocks.11.attn.to_add_out.bias": "model-00005.safetensors",
530
+ "transformer_blocks.11.attn.to_add_out.weight": "model-00005.safetensors",
531
+ "transformer_blocks.11.attn.to_k.bias": "model-00005.safetensors",
532
+ "transformer_blocks.11.attn.to_k.weight": "model-00005.safetensors",
533
+ "transformer_blocks.11.attn.to_out.0.bias": "model-00005.safetensors",
534
+ "transformer_blocks.11.attn.to_out.0.weight": "model-00005.safetensors",
535
+ "transformer_blocks.11.attn.to_q.bias": "model-00005.safetensors",
536
+ "transformer_blocks.11.attn.to_q.weight": "model-00005.safetensors",
537
+ "transformer_blocks.11.attn.to_v.bias": "model-00005.safetensors",
538
+ "transformer_blocks.11.attn.to_v.weight": "model-00005.safetensors",
539
+ "transformer_blocks.11.ff.net.0.proj.bias": "model-00005.safetensors",
540
+ "transformer_blocks.11.ff.net.0.proj.weight": "model-00005.safetensors",
541
+ "transformer_blocks.11.ff.net.2.bias": "model-00005.safetensors",
542
+ "transformer_blocks.11.ff.net.2.weight": "model-00005.safetensors",
543
+ "transformer_blocks.11.ff_context.net.0.proj.bias": "model-00005.safetensors",
544
+ "transformer_blocks.11.ff_context.net.0.proj.weight": "model-00005.safetensors",
545
+ "transformer_blocks.11.ff_context.net.2.bias": "model-00005.safetensors",
546
+ "transformer_blocks.11.ff_context.net.2.weight": "model-00005.safetensors",
547
+ "transformer_blocks.11.norm1.linear.bias": "model-00005.safetensors",
548
+ "transformer_blocks.11.norm1.linear.weight": "model-00005.safetensors",
549
+ "transformer_blocks.11.norm1_context.linear.bias": "model-00005.safetensors",
550
+ "transformer_blocks.11.norm1_context.linear.weight": "model-00005.safetensors",
551
+ "transformer_blocks.12.attn.add_k_proj.bias": "model-00005.safetensors",
552
+ "transformer_blocks.12.attn.add_k_proj.weight": "model-00005.safetensors",
553
+ "transformer_blocks.12.attn.add_q_proj.bias": "model-00005.safetensors",
554
+ "transformer_blocks.12.attn.add_q_proj.weight": "model-00005.safetensors",
555
+ "transformer_blocks.12.attn.add_v_proj.bias": "model-00005.safetensors",
556
+ "transformer_blocks.12.attn.add_v_proj.weight": "model-00005.safetensors",
557
+ "transformer_blocks.12.attn.norm_added_k.weight": "model-00005.safetensors",
558
+ "transformer_blocks.12.attn.norm_added_q.weight": "model-00005.safetensors",
559
+ "transformer_blocks.12.attn.norm_k.weight": "model-00005.safetensors",
560
+ "transformer_blocks.12.attn.norm_q.weight": "model-00005.safetensors",
561
+ "transformer_blocks.12.attn.to_add_out.bias": "model-00005.safetensors",
562
+ "transformer_blocks.12.attn.to_add_out.weight": "model-00005.safetensors",
563
+ "transformer_blocks.12.attn.to_k.bias": "model-00005.safetensors",
564
+ "transformer_blocks.12.attn.to_k.weight": "model-00005.safetensors",
565
+ "transformer_blocks.12.attn.to_out.0.bias": "model-00005.safetensors",
566
+ "transformer_blocks.12.attn.to_out.0.weight": "model-00005.safetensors",
567
+ "transformer_blocks.12.attn.to_q.bias": "model-00005.safetensors",
568
+ "transformer_blocks.12.attn.to_q.weight": "model-00005.safetensors",
569
+ "transformer_blocks.12.attn.to_v.bias": "model-00005.safetensors",
570
+ "transformer_blocks.12.attn.to_v.weight": "model-00005.safetensors",
571
+ "transformer_blocks.12.ff.net.0.proj.bias": "model-00005.safetensors",
572
+ "transformer_blocks.12.ff.net.0.proj.weight": "model-00005.safetensors",
573
+ "transformer_blocks.12.ff.net.2.bias": "model-00005.safetensors",
574
+ "transformer_blocks.12.ff.net.2.weight": "model-00005.safetensors",
575
+ "transformer_blocks.12.ff_context.net.0.proj.bias": "model-00005.safetensors",
576
+ "transformer_blocks.12.ff_context.net.0.proj.weight": "model-00005.safetensors",
577
+ "transformer_blocks.12.ff_context.net.2.bias": "model-00005.safetensors",
578
+ "transformer_blocks.12.ff_context.net.2.weight": "model-00005.safetensors",
579
+ "transformer_blocks.12.norm1.linear.bias": "model-00005.safetensors",
580
+ "transformer_blocks.12.norm1.linear.weight": "model-00005.safetensors",
581
+ "transformer_blocks.12.norm1_context.linear.bias": "model-00005.safetensors",
582
+ "transformer_blocks.12.norm1_context.linear.weight": "model-00006.safetensors",
583
+ "transformer_blocks.13.attn.add_k_proj.bias": "model-00006.safetensors",
584
+ "transformer_blocks.13.attn.add_k_proj.weight": "model-00006.safetensors",
585
+ "transformer_blocks.13.attn.add_q_proj.bias": "model-00006.safetensors",
586
+ "transformer_blocks.13.attn.add_q_proj.weight": "model-00006.safetensors",
587
+ "transformer_blocks.13.attn.add_v_proj.bias": "model-00006.safetensors",
588
+ "transformer_blocks.13.attn.add_v_proj.weight": "model-00006.safetensors",
589
+ "transformer_blocks.13.attn.norm_added_k.weight": "model-00006.safetensors",
590
+ "transformer_blocks.13.attn.norm_added_q.weight": "model-00006.safetensors",
591
+ "transformer_blocks.13.attn.norm_k.weight": "model-00006.safetensors",
592
+ "transformer_blocks.13.attn.norm_q.weight": "model-00006.safetensors",
593
+ "transformer_blocks.13.attn.to_add_out.bias": "model-00006.safetensors",
594
+ "transformer_blocks.13.attn.to_add_out.weight": "model-00006.safetensors",
595
+ "transformer_blocks.13.attn.to_k.bias": "model-00006.safetensors",
596
+ "transformer_blocks.13.attn.to_k.weight": "model-00006.safetensors",
597
+ "transformer_blocks.13.attn.to_out.0.bias": "model-00006.safetensors",
598
+ "transformer_blocks.13.attn.to_out.0.weight": "model-00006.safetensors",
599
+ "transformer_blocks.13.attn.to_q.bias": "model-00006.safetensors",
600
+ "transformer_blocks.13.attn.to_q.weight": "model-00006.safetensors",
601
+ "transformer_blocks.13.attn.to_v.bias": "model-00006.safetensors",
602
+ "transformer_blocks.13.attn.to_v.weight": "model-00006.safetensors",
603
+ "transformer_blocks.13.ff.net.0.proj.bias": "model-00006.safetensors",
604
+ "transformer_blocks.13.ff.net.0.proj.weight": "model-00006.safetensors",
605
+ "transformer_blocks.13.ff.net.2.bias": "model-00006.safetensors",
606
+ "transformer_blocks.13.ff.net.2.weight": "model-00006.safetensors",
607
+ "transformer_blocks.13.ff_context.net.0.proj.bias": "model-00006.safetensors",
608
+ "transformer_blocks.13.ff_context.net.0.proj.weight": "model-00006.safetensors",
609
+ "transformer_blocks.13.ff_context.net.2.bias": "model-00006.safetensors",
610
+ "transformer_blocks.13.ff_context.net.2.weight": "model-00006.safetensors",
611
+ "transformer_blocks.13.norm1.linear.bias": "model-00006.safetensors",
612
+ "transformer_blocks.13.norm1.linear.weight": "model-00006.safetensors",
613
+ "transformer_blocks.13.norm1_context.linear.bias": "model-00006.safetensors",
614
+ "transformer_blocks.13.norm1_context.linear.weight": "model-00006.safetensors",
615
+ "transformer_blocks.2.attn.add_k_proj.bias": "model-00006.safetensors",
616
+ "transformer_blocks.2.attn.add_k_proj.weight": "model-00006.safetensors",
617
+ "transformer_blocks.2.attn.add_q_proj.bias": "model-00006.safetensors",
618
+ "transformer_blocks.2.attn.add_q_proj.weight": "model-00006.safetensors",
619
+ "transformer_blocks.2.attn.add_v_proj.bias": "model-00006.safetensors",
620
+ "transformer_blocks.2.attn.add_v_proj.weight": "model-00006.safetensors",
621
+ "transformer_blocks.2.attn.norm_added_k.weight": "model-00006.safetensors",
622
+ "transformer_blocks.2.attn.norm_added_q.weight": "model-00006.safetensors",
623
+ "transformer_blocks.2.attn.norm_k.weight": "model-00006.safetensors",
624
+ "transformer_blocks.2.attn.norm_q.weight": "model-00006.safetensors",
625
+ "transformer_blocks.2.attn.to_add_out.bias": "model-00006.safetensors",
626
+ "transformer_blocks.2.attn.to_add_out.weight": "model-00006.safetensors",
627
+ "transformer_blocks.2.attn.to_k.bias": "model-00006.safetensors",
628
+ "transformer_blocks.2.attn.to_k.weight": "model-00006.safetensors",
629
+ "transformer_blocks.2.attn.to_out.0.bias": "model-00006.safetensors",
630
+ "transformer_blocks.2.attn.to_out.0.weight": "model-00006.safetensors",
631
+ "transformer_blocks.2.attn.to_q.bias": "model-00006.safetensors",
632
+ "transformer_blocks.2.attn.to_q.weight": "model-00006.safetensors",
633
+ "transformer_blocks.2.attn.to_v.bias": "model-00006.safetensors",
634
+ "transformer_blocks.2.attn.to_v.weight": "model-00006.safetensors",
635
+ "transformer_blocks.2.ff.net.0.proj.bias": "model-00006.safetensors",
636
+ "transformer_blocks.2.ff.net.0.proj.weight": "model-00006.safetensors",
637
+ "transformer_blocks.2.ff.net.2.bias": "model-00006.safetensors",
638
+ "transformer_blocks.2.ff.net.2.weight": "model-00006.safetensors",
639
+ "transformer_blocks.2.ff_context.net.0.proj.bias": "model-00006.safetensors",
640
+ "transformer_blocks.2.ff_context.net.0.proj.weight": "model-00006.safetensors",
641
+ "transformer_blocks.2.ff_context.net.2.bias": "model-00006.safetensors",
642
+ "transformer_blocks.2.ff_context.net.2.weight": "model-00006.safetensors",
643
+ "transformer_blocks.2.norm1.linear.bias": "model-00006.safetensors",
644
+ "transformer_blocks.2.norm1.linear.weight": "model-00006.safetensors",
645
+ "transformer_blocks.2.norm1_context.linear.bias": "model-00006.safetensors",
646
+ "transformer_blocks.2.norm1_context.linear.weight": "model-00006.safetensors",
647
+ "transformer_blocks.3.attn.add_k_proj.bias": "model-00006.safetensors",
648
+ "transformer_blocks.3.attn.add_k_proj.weight": "model-00006.safetensors",
649
+ "transformer_blocks.3.attn.add_q_proj.bias": "model-00006.safetensors",
650
+ "transformer_blocks.3.attn.add_q_proj.weight": "model-00006.safetensors",
651
+ "transformer_blocks.3.attn.add_v_proj.bias": "model-00006.safetensors",
652
+ "transformer_blocks.3.attn.add_v_proj.weight": "model-00006.safetensors",
653
+ "transformer_blocks.3.attn.norm_added_k.weight": "model-00006.safetensors",
654
+ "transformer_blocks.3.attn.norm_added_q.weight": "model-00006.safetensors",
655
+ "transformer_blocks.3.attn.norm_k.weight": "model-00006.safetensors",
656
+ "transformer_blocks.3.attn.norm_q.weight": "model-00006.safetensors",
657
+ "transformer_blocks.3.attn.to_add_out.bias": "model-00006.safetensors",
658
+ "transformer_blocks.3.attn.to_add_out.weight": "model-00006.safetensors",
659
+ "transformer_blocks.3.attn.to_k.bias": "model-00006.safetensors",
660
+ "transformer_blocks.3.attn.to_k.weight": "model-00006.safetensors",
661
+ "transformer_blocks.3.attn.to_out.0.bias": "model-00006.safetensors",
662
+ "transformer_blocks.3.attn.to_out.0.weight": "model-00006.safetensors",
663
+ "transformer_blocks.3.attn.to_q.bias": "model-00006.safetensors",
664
+ "transformer_blocks.3.attn.to_q.weight": "model-00006.safetensors",
665
+ "transformer_blocks.3.attn.to_v.bias": "model-00006.safetensors",
666
+ "transformer_blocks.3.attn.to_v.weight": "model-00006.safetensors",
667
+ "transformer_blocks.3.ff.net.0.proj.bias": "model-00006.safetensors",
668
+ "transformer_blocks.3.ff.net.0.proj.weight": "model-00006.safetensors",
669
+ "transformer_blocks.3.ff.net.2.bias": "model-00006.safetensors",
670
+ "transformer_blocks.3.ff.net.2.weight": "model-00006.safetensors",
671
+ "transformer_blocks.3.ff_context.net.0.proj.bias": "model-00006.safetensors",
672
+ "transformer_blocks.3.ff_context.net.0.proj.weight": "model-00006.safetensors",
673
+ "transformer_blocks.3.ff_context.net.2.bias": "model-00006.safetensors",
674
+ "transformer_blocks.3.ff_context.net.2.weight": "model-00006.safetensors",
675
+ "transformer_blocks.3.norm1.linear.bias": "model-00006.safetensors",
676
+ "transformer_blocks.3.norm1.linear.weight": "model-00006.safetensors",
677
+ "transformer_blocks.3.norm1_context.linear.bias": "model-00006.safetensors",
678
+ "transformer_blocks.3.norm1_context.linear.weight": "model-00006.safetensors",
679
+ "transformer_blocks.4.attn.add_k_proj.bias": "model-00006.safetensors",
680
+ "transformer_blocks.4.attn.add_k_proj.weight": "model-00006.safetensors",
681
+ "transformer_blocks.4.attn.add_q_proj.bias": "model-00006.safetensors",
682
+ "transformer_blocks.4.attn.add_q_proj.weight": "model-00006.safetensors",
683
+ "transformer_blocks.4.attn.add_v_proj.bias": "model-00006.safetensors",
684
+ "transformer_blocks.4.attn.add_v_proj.weight": "model-00006.safetensors",
685
+ "transformer_blocks.4.attn.norm_added_k.weight": "model-00006.safetensors",
686
+ "transformer_blocks.4.attn.norm_added_q.weight": "model-00006.safetensors",
687
+ "transformer_blocks.4.attn.norm_k.weight": "model-00006.safetensors",
688
+ "transformer_blocks.4.attn.norm_q.weight": "model-00006.safetensors",
689
+ "transformer_blocks.4.attn.to_add_out.bias": "model-00006.safetensors",
690
+ "transformer_blocks.4.attn.to_add_out.weight": "model-00006.safetensors",
691
+ "transformer_blocks.4.attn.to_k.bias": "model-00006.safetensors",
692
+ "transformer_blocks.4.attn.to_k.weight": "model-00006.safetensors",
693
+ "transformer_blocks.4.attn.to_out.0.bias": "model-00006.safetensors",
694
+ "transformer_blocks.4.attn.to_out.0.weight": "model-00006.safetensors",
695
+ "transformer_blocks.4.attn.to_q.bias": "model-00006.safetensors",
696
+ "transformer_blocks.4.attn.to_q.weight": "model-00006.safetensors",
697
+ "transformer_blocks.4.attn.to_v.bias": "model-00006.safetensors",
698
+ "transformer_blocks.4.attn.to_v.weight": "model-00006.safetensors",
699
+ "transformer_blocks.4.ff.net.0.proj.bias": "model-00006.safetensors",
700
+ "transformer_blocks.4.ff.net.0.proj.weight": "model-00006.safetensors",
701
+ "transformer_blocks.4.ff.net.2.bias": "model-00006.safetensors",
702
+ "transformer_blocks.4.ff.net.2.weight": "model-00007.safetensors",
703
+ "transformer_blocks.4.ff_context.net.0.proj.bias": "model-00007.safetensors",
704
+ "transformer_blocks.4.ff_context.net.0.proj.weight": "model-00007.safetensors",
705
+ "transformer_blocks.4.ff_context.net.2.bias": "model-00007.safetensors",
706
+ "transformer_blocks.4.ff_context.net.2.weight": "model-00007.safetensors",
707
+ "transformer_blocks.4.norm1.linear.bias": "model-00007.safetensors",
708
+ "transformer_blocks.4.norm1.linear.weight": "model-00007.safetensors",
709
+ "transformer_blocks.4.norm1_context.linear.bias": "model-00007.safetensors",
710
+ "transformer_blocks.4.norm1_context.linear.weight": "model-00007.safetensors",
711
+ "transformer_blocks.5.attn.add_k_proj.bias": "model-00007.safetensors",
712
+ "transformer_blocks.5.attn.add_k_proj.weight": "model-00007.safetensors",
713
+ "transformer_blocks.5.attn.add_q_proj.bias": "model-00007.safetensors",
714
+ "transformer_blocks.5.attn.add_q_proj.weight": "model-00007.safetensors",
715
+ "transformer_blocks.5.attn.add_v_proj.bias": "model-00007.safetensors",
716
+ "transformer_blocks.5.attn.add_v_proj.weight": "model-00007.safetensors",
717
+ "transformer_blocks.5.attn.norm_added_k.weight": "model-00007.safetensors",
718
+ "transformer_blocks.5.attn.norm_added_q.weight": "model-00007.safetensors",
719
+ "transformer_blocks.5.attn.norm_k.weight": "model-00007.safetensors",
720
+ "transformer_blocks.5.attn.norm_q.weight": "model-00007.safetensors",
721
+ "transformer_blocks.5.attn.to_add_out.bias": "model-00007.safetensors",
722
+ "transformer_blocks.5.attn.to_add_out.weight": "model-00007.safetensors",
723
+ "transformer_blocks.5.attn.to_k.bias": "model-00007.safetensors",
724
+ "transformer_blocks.5.attn.to_k.weight": "model-00007.safetensors",
725
+ "transformer_blocks.5.attn.to_out.0.bias": "model-00007.safetensors",
726
+ "transformer_blocks.5.attn.to_out.0.weight": "model-00007.safetensors",
727
+ "transformer_blocks.5.attn.to_q.bias": "model-00007.safetensors",
728
+ "transformer_blocks.5.attn.to_q.weight": "model-00007.safetensors",
729
+ "transformer_blocks.5.attn.to_v.bias": "model-00007.safetensors",
730
+ "transformer_blocks.5.attn.to_v.weight": "model-00007.safetensors",
731
+ "transformer_blocks.5.ff.net.0.proj.bias": "model-00007.safetensors",
732
+ "transformer_blocks.5.ff.net.0.proj.weight": "model-00007.safetensors",
733
+ "transformer_blocks.5.ff.net.2.bias": "model-00007.safetensors",
734
+ "transformer_blocks.5.ff.net.2.weight": "model-00007.safetensors",
735
+ "transformer_blocks.5.ff_context.net.0.proj.bias": "model-00007.safetensors",
736
+ "transformer_blocks.5.ff_context.net.0.proj.weight": "model-00007.safetensors",
737
+ "transformer_blocks.5.ff_context.net.2.bias": "model-00007.safetensors",
738
+ "transformer_blocks.5.ff_context.net.2.weight": "model-00007.safetensors",
739
+ "transformer_blocks.5.norm1.linear.bias": "model-00007.safetensors",
740
+ "transformer_blocks.5.norm1.linear.weight": "model-00007.safetensors",
741
+ "transformer_blocks.5.norm1_context.linear.bias": "model-00007.safetensors",
742
+ "transformer_blocks.5.norm1_context.linear.weight": "model-00007.safetensors",
743
+ "transformer_blocks.6.attn.add_k_proj.bias": "model-00007.safetensors",
744
+ "transformer_blocks.6.attn.add_k_proj.weight": "model-00007.safetensors",
745
+ "transformer_blocks.6.attn.add_q_proj.bias": "model-00007.safetensors",
746
+ "transformer_blocks.6.attn.add_q_proj.weight": "model-00007.safetensors",
747
+ "transformer_blocks.6.attn.add_v_proj.bias": "model-00007.safetensors",
748
+ "transformer_blocks.6.attn.add_v_proj.weight": "model-00007.safetensors",
749
+ "transformer_blocks.6.attn.norm_added_k.weight": "model-00007.safetensors",
750
+ "transformer_blocks.6.attn.norm_added_q.weight": "model-00007.safetensors",
751
+ "transformer_blocks.6.attn.norm_k.weight": "model-00007.safetensors",
752
+ "transformer_blocks.6.attn.norm_q.weight": "model-00007.safetensors",
753
+ "transformer_blocks.6.attn.to_add_out.bias": "model-00007.safetensors",
754
+ "transformer_blocks.6.attn.to_add_out.weight": "model-00007.safetensors",
755
+ "transformer_blocks.6.attn.to_k.bias": "model-00007.safetensors",
756
+ "transformer_blocks.6.attn.to_k.weight": "model-00007.safetensors",
757
+ "transformer_blocks.6.attn.to_out.0.bias": "model-00007.safetensors",
758
+ "transformer_blocks.6.attn.to_out.0.weight": "model-00007.safetensors",
759
+ "transformer_blocks.6.attn.to_q.bias": "model-00007.safetensors",
760
+ "transformer_blocks.6.attn.to_q.weight": "model-00007.safetensors",
761
+ "transformer_blocks.6.attn.to_v.bias": "model-00007.safetensors",
762
+ "transformer_blocks.6.attn.to_v.weight": "model-00007.safetensors",
763
+ "transformer_blocks.6.ff.net.0.proj.bias": "model-00007.safetensors",
764
+ "transformer_blocks.6.ff.net.0.proj.weight": "model-00007.safetensors",
765
+ "transformer_blocks.6.ff.net.2.bias": "model-00007.safetensors",
766
+ "transformer_blocks.6.ff.net.2.weight": "model-00007.safetensors",
767
+ "transformer_blocks.6.ff_context.net.0.proj.bias": "model-00007.safetensors",
768
+ "transformer_blocks.6.ff_context.net.0.proj.weight": "model-00007.safetensors",
769
+ "transformer_blocks.6.ff_context.net.2.bias": "model-00007.safetensors",
770
+ "transformer_blocks.6.ff_context.net.2.weight": "model-00007.safetensors",
771
+ "transformer_blocks.6.norm1.linear.bias": "model-00007.safetensors",
772
+ "transformer_blocks.6.norm1.linear.weight": "model-00007.safetensors",
773
+ "transformer_blocks.6.norm1_context.linear.bias": "model-00007.safetensors",
774
+ "transformer_blocks.6.norm1_context.linear.weight": "model-00007.safetensors",
775
+ "transformer_blocks.7.attn.add_k_proj.bias": "model-00007.safetensors",
776
+ "transformer_blocks.7.attn.add_k_proj.weight": "model-00007.safetensors",
777
+ "transformer_blocks.7.attn.add_q_proj.bias": "model-00007.safetensors",
778
+ "transformer_blocks.7.attn.add_q_proj.weight": "model-00007.safetensors",
779
+ "transformer_blocks.7.attn.add_v_proj.bias": "model-00007.safetensors",
780
+ "transformer_blocks.7.attn.add_v_proj.weight": "model-00007.safetensors",
781
+ "transformer_blocks.7.attn.norm_added_k.weight": "model-00007.safetensors",
782
+ "transformer_blocks.7.attn.norm_added_q.weight": "model-00007.safetensors",
783
+ "transformer_blocks.7.attn.norm_k.weight": "model-00007.safetensors",
784
+ "transformer_blocks.7.attn.norm_q.weight": "model-00007.safetensors",
785
+ "transformer_blocks.7.attn.to_add_out.bias": "model-00007.safetensors",
786
+ "transformer_blocks.7.attn.to_add_out.weight": "model-00007.safetensors",
787
+ "transformer_blocks.7.attn.to_k.bias": "model-00007.safetensors",
788
+ "transformer_blocks.7.attn.to_k.weight": "model-00007.safetensors",
789
+ "transformer_blocks.7.attn.to_out.0.bias": "model-00007.safetensors",
790
+ "transformer_blocks.7.attn.to_out.0.weight": "model-00007.safetensors",
791
+ "transformer_blocks.7.attn.to_q.bias": "model-00007.safetensors",
792
+ "transformer_blocks.7.attn.to_q.weight": "model-00007.safetensors",
793
+ "transformer_blocks.7.attn.to_v.bias": "model-00007.safetensors",
794
+ "transformer_blocks.7.attn.to_v.weight": "model-00007.safetensors",
795
+ "transformer_blocks.7.ff.net.0.proj.bias": "model-00007.safetensors",
796
+ "transformer_blocks.7.ff.net.0.proj.weight": "model-00007.safetensors",
797
+ "transformer_blocks.7.ff.net.2.bias": "model-00007.safetensors",
798
+ "transformer_blocks.7.ff.net.2.weight": "model-00007.safetensors",
799
+ "transformer_blocks.7.ff_context.net.0.proj.bias": "model-00007.safetensors",
800
+ "transformer_blocks.7.ff_context.net.0.proj.weight": "model-00007.safetensors",
801
+ "transformer_blocks.7.ff_context.net.2.bias": "model-00007.safetensors",
802
+ "transformer_blocks.7.ff_context.net.2.weight": "model-00007.safetensors",
803
+ "transformer_blocks.7.norm1.linear.bias": "model-00007.safetensors",
804
+ "transformer_blocks.7.norm1.linear.weight": "model-00007.safetensors",
805
+ "transformer_blocks.7.norm1_context.linear.bias": "model-00007.safetensors",
806
+ "transformer_blocks.7.norm1_context.linear.weight": "model-00008.safetensors",
807
+ "transformer_blocks.8.attn.add_k_proj.bias": "model-00008.safetensors",
808
+ "transformer_blocks.8.attn.add_k_proj.weight": "model-00008.safetensors",
809
+ "transformer_blocks.8.attn.add_q_proj.bias": "model-00008.safetensors",
810
+ "transformer_blocks.8.attn.add_q_proj.weight": "model-00008.safetensors",
811
+ "transformer_blocks.8.attn.add_v_proj.bias": "model-00008.safetensors",
812
+ "transformer_blocks.8.attn.add_v_proj.weight": "model-00008.safetensors",
813
+ "transformer_blocks.8.attn.norm_added_k.weight": "model-00008.safetensors",
814
+ "transformer_blocks.8.attn.norm_added_q.weight": "model-00008.safetensors",
815
+ "transformer_blocks.8.attn.norm_k.weight": "model-00008.safetensors",
816
+ "transformer_blocks.8.attn.norm_q.weight": "model-00008.safetensors",
817
+ "transformer_blocks.8.attn.to_add_out.bias": "model-00008.safetensors",
818
+ "transformer_blocks.8.attn.to_add_out.weight": "model-00008.safetensors",
819
+ "transformer_blocks.8.attn.to_k.bias": "model-00008.safetensors",
820
+ "transformer_blocks.8.attn.to_k.weight": "model-00008.safetensors",
821
+ "transformer_blocks.8.attn.to_out.0.bias": "model-00008.safetensors",
822
+ "transformer_blocks.8.attn.to_out.0.weight": "model-00008.safetensors",
823
+ "transformer_blocks.8.attn.to_q.bias": "model-00008.safetensors",
824
+ "transformer_blocks.8.attn.to_q.weight": "model-00008.safetensors",
825
+ "transformer_blocks.8.attn.to_v.bias": "model-00008.safetensors",
826
+ "transformer_blocks.8.attn.to_v.weight": "model-00008.safetensors",
827
+ "transformer_blocks.8.ff.net.0.proj.bias": "model-00008.safetensors",
828
+ "transformer_blocks.8.ff.net.0.proj.weight": "model-00008.safetensors",
829
+ "transformer_blocks.8.ff.net.2.bias": "model-00008.safetensors",
830
+ "transformer_blocks.8.ff.net.2.weight": "model-00008.safetensors",
831
+ "transformer_blocks.8.ff_context.net.0.proj.bias": "model-00008.safetensors",
832
+ "transformer_blocks.8.ff_context.net.0.proj.weight": "model-00008.safetensors",
833
+ "transformer_blocks.8.ff_context.net.2.bias": "model-00008.safetensors",
834
+ "transformer_blocks.8.ff_context.net.2.weight": "model-00008.safetensors",
835
+ "transformer_blocks.8.norm1.linear.bias": "model-00008.safetensors",
836
+ "transformer_blocks.8.norm1.linear.weight": "model-00008.safetensors",
837
+ "transformer_blocks.8.norm1_context.linear.bias": "model-00008.safetensors",
838
+ "transformer_blocks.8.norm1_context.linear.weight": "model-00008.safetensors",
839
+ "transformer_blocks.9.attn.add_k_proj.bias": "model-00008.safetensors",
840
+ "transformer_blocks.9.attn.add_k_proj.weight": "model-00008.safetensors",
841
+ "transformer_blocks.9.attn.add_q_proj.bias": "model-00008.safetensors",
842
+ "transformer_blocks.9.attn.add_q_proj.weight": "model-00008.safetensors",
843
+ "transformer_blocks.9.attn.add_v_proj.bias": "model-00008.safetensors",
844
+ "transformer_blocks.9.attn.add_v_proj.weight": "model-00008.safetensors",
845
+ "transformer_blocks.9.attn.norm_added_k.weight": "model-00008.safetensors",
846
+ "transformer_blocks.9.attn.norm_added_q.weight": "model-00008.safetensors",
847
+ "transformer_blocks.9.attn.norm_k.weight": "model-00008.safetensors",
848
+ "transformer_blocks.9.attn.norm_q.weight": "model-00008.safetensors",
849
+ "transformer_blocks.9.attn.to_add_out.bias": "model-00008.safetensors",
850
+ "transformer_blocks.9.attn.to_add_out.weight": "model-00008.safetensors",
851
+ "transformer_blocks.9.attn.to_k.bias": "model-00008.safetensors",
852
+ "transformer_blocks.9.attn.to_k.weight": "model-00008.safetensors",
853
+ "transformer_blocks.9.attn.to_out.0.bias": "model-00008.safetensors",
854
+ "transformer_blocks.9.attn.to_out.0.weight": "model-00008.safetensors",
855
+ "transformer_blocks.9.attn.to_q.bias": "model-00008.safetensors",
856
+ "transformer_blocks.9.attn.to_q.weight": "model-00008.safetensors",
857
+ "transformer_blocks.9.attn.to_v.bias": "model-00008.safetensors",
858
+ "transformer_blocks.9.attn.to_v.weight": "model-00008.safetensors",
859
+ "transformer_blocks.9.ff.net.0.proj.bias": "model-00008.safetensors",
860
+ "transformer_blocks.9.ff.net.0.proj.weight": "model-00008.safetensors",
861
+ "transformer_blocks.9.ff.net.2.bias": "model-00008.safetensors",
862
+ "transformer_blocks.9.ff.net.2.weight": "model-00008.safetensors",
863
+ "transformer_blocks.9.ff_context.net.0.proj.bias": "model-00008.safetensors",
864
+ "transformer_blocks.9.ff_context.net.0.proj.weight": "model-00008.safetensors",
865
+ "transformer_blocks.9.ff_context.net.2.bias": "model-00008.safetensors",
866
+ "transformer_blocks.9.ff_context.net.2.weight": "model-00008.safetensors",
867
+ "transformer_blocks.9.norm1.linear.bias": "model-00008.safetensors",
868
+ "transformer_blocks.9.norm1.linear.weight": "model-00008.safetensors",
869
+ "transformer_blocks.9.norm1_context.linear.bias": "model-00008.safetensors",
870
+ "transformer_blocks.9.norm1_context.linear.weight": "model-00008.safetensors",
871
+ "up_block.upsample.conv.weight": "model-00008.safetensors",
872
+ "up_block.upsample.norm.weight": "model-00008.safetensors"
873
+ }
874
+ }
editmgt-e3-dense-fp32-epoch1.5-step9375/training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31470f48f62cecad480838783b614bc0028054d9e46db2849bc1ad965ec46e59
3
+ size 8075517310