Hugging Face's logo

AbstractFramework
/
wan2.2-ti2v-5b-diffusers-8bit

Text-to-Video
Safetensors
MLX
Wan2.2
mlx-gen
mflux
apple-silicon
8-bit precision
wan
video-generation
image-to-video
Model card Files
xet
 Community
lpalbou commited on
Commit
0627bf7
·
verified ·
1 Parent(s): 7f2035a

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. README.md +77 -0
  3. model_index.json +30 -0
  4. scheduler/scheduler_config.json +30 -0
  5. text_encoder/config.json +34 -0
  6. text_encoder/model-00001-of-00003.safetensors +3 -0
  7. text_encoder/model-00002-of-00003.safetensors +3 -0
  8. text_encoder/model-00003-of-00003.safetensors +3 -0
  9. text_encoder/model.safetensors.index.json +249 -0
  10. tokenizer/tokenizer.json +3 -0
  11. tokenizer/tokenizer_config.json +317 -0
  12. transformer/0.safetensors +3 -0
  13. transformer/1.safetensors +3 -0
  14. transformer/2.safetensors +3 -0
  15. transformer/model.safetensors.index.json +1447 -0
  16. vae/0.safetensors +3 -0
  17. vae/model.safetensors.index.json +204 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Wan-AI/Wan2.2-TI2V-5B-Diffusers
4
+ pipeline_tag: text-to-video
5
+ library_name: mlx-gen
6
+ tags:
7
+ - mlx
8
+ - mlx-gen
9
+ - mflux
10
+ - apple-silicon
11
+ - 8-bit
12
+ - wan
13
+ - wan2.2
14
+ - video-generation
15
+ - text-to-video
16
+ - image-to-video
17
+ ---
18
+ # wan2.2-ti2v-5b-diffusers-8bit
19
+
20
+ This repository contains MLX-Gen saved weights for `Wan-AI/Wan2.2-TI2V-5B-Diffusers`. The checkpoint is designed for local Apple Silicon inference with [`mlx-gen`](https://github.com/lpalbou/mlx-gen).
21
+
22
+ It uses the mflux/MLX saved-weight layout and MLX quantization tensors. It is not a Diffusers or Transformers `from_pretrained()` checkpoint.
23
+
24
+ ## Source Model
25
+
26
+ Original model: [`Wan-AI/Wan2.2-TI2V-5B-Diffusers`](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers).
27
+
28
+ ## License and Access
29
+
30
+ This quantized derivative follows the Apache 2.0 license of the source model.
31
+
32
+ ## Quantization
33
+
34
+ This is an MLX q8 checkpoint for Wan2.2 TI2V. MLX-Gen uses 8-bit quantization for Wan modules where MLX supports quantization:
35
+
36
+ - q8 for quantizable Wan transformer modules.
37
+ - q8 for quantizable Wan VAE modules.
38
+ - BF16 for the UMT5 text encoder, scheduler metadata, tokenizer files, norms, and other non-quantizable parameters.
39
+
40
+ Wan q4 quality and any possible mixed q4/q8 policy are still under validation. Prefer q8 for publishable Wan checkpoints until the q4 policy is documented.
41
+
42
+ See the [MLX-Gen quantization docs](https://github.com/lpalbou/mlx-gen/blob/main/docs/quantization.md) for compatibility notes.
43
+
44
+ ## Compatibility
45
+
46
+ Requires `mlx-gen >= 0.18.6`.
47
+
48
+ Generated with `mlx-gen 0.18.6`.
49
+
50
+ Use the `mlxgen` command and Python import path for new MLX-Gen projects.
51
+
52
+ ## Usage
53
+
54
+ ```bash
55
+ python -m pip install -U mlx-gen
56
+
57
+ mlxgen download --model AbstractFramework/wan2.2-ti2v-5b-diffusers-8bit
58
+
59
+ mlxgen generate \
60
+ --model AbstractFramework/wan2.2-ti2v-5b-diffusers-8bit \
61
+ --task text-to-video \
62
+ --prompt "Your video prompt here" \
63
+ --width 1280 \
64
+ --height 704 \
65
+ --frames 121 \
66
+ --steps 50 \
67
+ --guidance 5 \
68
+ --fps 24 \
69
+ --seed 42 \
70
+ --output video.mp4
71
+ ```
72
+
73
+ ## Attribution
74
+
75
+ MLX-Gen is based on [mflux](https://github.com/filipstrand/mflux) by Filip Strand and the original mflux contributors. This model card is generated by MLX-Gen so derived checkpoints keep that attribution visible.
76
+
77
+ Quantized and contributed by [@lpalbou](https://huggingface.co/lpalbou).
model_index.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "WanPipeline",
3
+ "_diffusers_version": "0.35.0.dev0",
4
+ "boundary_ratio": null,
5
+ "expand_timesteps": true,
6
+ "scheduler": [
7
+ "diffusers",
8
+ "UniPCMultistepScheduler"
9
+ ],
10
+ "text_encoder": [
11
+ "transformers",
12
+ "UMT5EncoderModel"
13
+ ],
14
+ "tokenizer": [
15
+ "transformers",
16
+ "T5TokenizerFast"
17
+ ],
18
+ "transformer": [
19
+ "diffusers",
20
+ "WanTransformer3DModel"
21
+ ],
22
+ "transformer_2": [
23
+ null,
24
+ null
25
+ ],
26
+ "vae": [
27
+ "diffusers",
28
+ "AutoencoderKLWan"
29
+ ]
30
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UniPCMultistepScheduler",
3
+ "_diffusers_version": "0.35.0.dev0",
4
+ "beta_end": 0.02,
5
+ "beta_schedule": "linear",
6
+ "beta_start": 0.0001,
7
+ "disable_corrector": [],
8
+ "dynamic_thresholding_ratio": 0.995,
9
+ "final_sigmas_type": "zero",
10
+ "flow_shift": 5.0,
11
+ "lower_order_final": true,
12
+ "num_train_timesteps": 1000,
13
+ "predict_x0": true,
14
+ "prediction_type": "flow_prediction",
15
+ "rescale_betas_zero_snr": false,
16
+ "sample_max_value": 1.0,
17
+ "solver_order": 2,
18
+ "solver_p": null,
19
+ "solver_type": "bh2",
20
+ "steps_offset": 0,
21
+ "thresholding": false,
22
+ "time_shift_type": "exponential",
23
+ "timestep_spacing": "linspace",
24
+ "trained_betas": null,
25
+ "use_beta_sigmas": false,
26
+ "use_dynamic_shifting": false,
27
+ "use_exponential_sigmas": false,
28
+ "use_flow_sigmas": true,
29
+ "use_karras_sigmas": false
30
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/umt5-xxl",
3
+ "architectures": [
4
+ "UMT5EncoderModel"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "umt5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "scalable_attention": true,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "T5Tokenizer",
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.48.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 256384
34
+ }
text_encoder/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e861969c7433e707cc5a74065d795d36cca07ec96eb6763eb4083df7248f58
3
+ size 4935812536
text_encoder/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57d948ece4837d850b7a859a4415121d57cacf8b9ee1d4db200c67f592902d7
3
+ size 4983103192
text_encoder/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da9ee284e21d1406df708788db1d502d95d75f69faa25cd26151bf8829b7c5f
3
+ size 1442935480
text_encoder/model.safetensors.index.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11361820672
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
20
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
21
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
24
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
25
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
29
+ "encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
30
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
31
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
33
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
34
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
35
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
38
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
39
+ "encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
40
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
41
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
42
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
43
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
44
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
45
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
47
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
48
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
49
+ "encoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
50
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
51
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
52
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
53
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
54
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
55
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
56
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
57
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
58
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
59
+ "encoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
60
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
61
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
62
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
63
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
64
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
65
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
66
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
67
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
68
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
69
+ "encoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
70
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
71
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
72
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
73
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
74
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
75
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
76
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
77
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
78
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
79
+ "encoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
80
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
81
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
82
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
83
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
84
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
85
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
86
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
87
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
88
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
89
+ "encoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
90
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
91
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
92
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
93
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
94
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
95
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
96
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
97
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
98
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
99
+ "encoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
100
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
101
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
102
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
103
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
104
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
105
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
106
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
107
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
108
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
109
+ "encoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
110
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
111
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
112
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
113
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
114
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
115
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
116
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
117
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
118
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
119
+ "encoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
120
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
121
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
122
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
123
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
124
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
125
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
126
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
127
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
128
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
129
+ "encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
130
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
131
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
132
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
133
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
134
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
135
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
136
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
137
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
138
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
139
+ "encoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
140
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
141
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
142
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
143
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
144
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
145
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
146
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
147
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
148
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
149
+ "encoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
150
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
151
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
152
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
153
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
154
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
155
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
156
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
157
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
158
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
159
+ "encoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
160
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
161
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
162
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
163
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
164
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
165
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
166
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
167
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
168
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
169
+ "encoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00003.safetensors",
170
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
171
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
172
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
173
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
174
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
175
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
176
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
177
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
178
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
179
+ "encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
180
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
181
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
182
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
183
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
184
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
185
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
186
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
187
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
188
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
189
+ "encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
190
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
191
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
192
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
193
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
194
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
195
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
196
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
197
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
198
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
199
+ "encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
200
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
201
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
202
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
203
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
204
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
205
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
206
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
207
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
208
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
209
+ "encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
210
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
211
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
212
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
213
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
214
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
215
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
216
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
217
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
218
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
219
+ "encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
220
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
221
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
222
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
223
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
224
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
225
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
226
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
227
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
228
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
229
+ "encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
230
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
231
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
232
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
233
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
234
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
235
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
236
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
237
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
238
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
239
+ "encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
240
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
241
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
242
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
243
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
244
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
245
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
246
+ "encoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
247
+ "shared.weight": "model-00001-of-00003.safetensors"
248
+ }
249
+ }
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87c960c36d5fbf4e7e76c2469b7eab877be7f8c5992efbf97e44d3123cc6521
3
+ size 16837418
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "</s>",
6
+ "extra_ids": 300,
7
+ "extra_special_tokens": [
8
+ "<extra_id_0>",
9
+ "<extra_id_1>",
10
+ "<extra_id_2>",
11
+ "<extra_id_3>",
12
+ "<extra_id_4>",
13
+ "<extra_id_5>",
14
+ "<extra_id_6>",
15
+ "<extra_id_7>",
16
+ "<extra_id_8>",
17
+ "<extra_id_9>",
18
+ "<extra_id_10>",
19
+ "<extra_id_11>",
20
+ "<extra_id_12>",
21
+ "<extra_id_13>",
22
+ "<extra_id_14>",
23
+ "<extra_id_15>",
24
+ "<extra_id_16>",
25
+ "<extra_id_17>",
26
+ "<extra_id_18>",
27
+ "<extra_id_19>",
28
+ "<extra_id_20>",
29
+ "<extra_id_21>",
30
+ "<extra_id_22>",
31
+ "<extra_id_23>",
32
+ "<extra_id_24>",
33
+ "<extra_id_25>",
34
+ "<extra_id_26>",
35
+ "<extra_id_27>",
36
+ "<extra_id_28>",
37
+ "<extra_id_29>",
38
+ "<extra_id_30>",
39
+ "<extra_id_31>",
40
+ "<extra_id_32>",
41
+ "<extra_id_33>",
42
+ "<extra_id_34>",
43
+ "<extra_id_35>",
44
+ "<extra_id_36>",
45
+ "<extra_id_37>",
46
+ "<extra_id_38>",
47
+ "<extra_id_39>",
48
+ "<extra_id_40>",
49
+ "<extra_id_41>",
50
+ "<extra_id_42>",
51
+ "<extra_id_43>",
52
+ "<extra_id_44>",
53
+ "<extra_id_45>",
54
+ "<extra_id_46>",
55
+ "<extra_id_47>",
56
+ "<extra_id_48>",
57
+ "<extra_id_49>",
58
+ "<extra_id_50>",
59
+ "<extra_id_51>",
60
+ "<extra_id_52>",
61
+ "<extra_id_53>",
62
+ "<extra_id_54>",
63
+ "<extra_id_55>",
64
+ "<extra_id_56>",
65
+ "<extra_id_57>",
66
+ "<extra_id_58>",
67
+ "<extra_id_59>",
68
+ "<extra_id_60>",
69
+ "<extra_id_61>",
70
+ "<extra_id_62>",
71
+ "<extra_id_63>",
72
+ "<extra_id_64>",
73
+ "<extra_id_65>",
74
+ "<extra_id_66>",
75
+ "<extra_id_67>",
76
+ "<extra_id_68>",
77
+ "<extra_id_69>",
78
+ "<extra_id_70>",
79
+ "<extra_id_71>",
80
+ "<extra_id_72>",
81
+ "<extra_id_73>",
82
+ "<extra_id_74>",
83
+ "<extra_id_75>",
84
+ "<extra_id_76>",
85
+ "<extra_id_77>",
86
+ "<extra_id_78>",
87
+ "<extra_id_79>",
88
+ "<extra_id_80>",
89
+ "<extra_id_81>",
90
+ "<extra_id_82>",
91
+ "<extra_id_83>",
92
+ "<extra_id_84>",
93
+ "<extra_id_85>",
94
+ "<extra_id_86>",
95
+ "<extra_id_87>",
96
+ "<extra_id_88>",
97
+ "<extra_id_89>",
98
+ "<extra_id_90>",
99
+ "<extra_id_91>",
100
+ "<extra_id_92>",
101
+ "<extra_id_93>",
102
+ "<extra_id_94>",
103
+ "<extra_id_95>",
104
+ "<extra_id_96>",
105
+ "<extra_id_97>",
106
+ "<extra_id_98>",
107
+ "<extra_id_99>",
108
+ "<extra_id_100>",
109
+ "<extra_id_101>",
110
+ "<extra_id_102>",
111
+ "<extra_id_103>",
112
+ "<extra_id_104>",
113
+ "<extra_id_105>",
114
+ "<extra_id_106>",
115
+ "<extra_id_107>",
116
+ "<extra_id_108>",
117
+ "<extra_id_109>",
118
+ "<extra_id_110>",
119
+ "<extra_id_111>",
120
+ "<extra_id_112>",
121
+ "<extra_id_113>",
122
+ "<extra_id_114>",
123
+ "<extra_id_115>",
124
+ "<extra_id_116>",
125
+ "<extra_id_117>",
126
+ "<extra_id_118>",
127
+ "<extra_id_119>",
128
+ "<extra_id_120>",
129
+ "<extra_id_121>",
130
+ "<extra_id_122>",
131
+ "<extra_id_123>",
132
+ "<extra_id_124>",
133
+ "<extra_id_125>",
134
+ "<extra_id_126>",
135
+ "<extra_id_127>",
136
+ "<extra_id_128>",
137
+ "<extra_id_129>",
138
+ "<extra_id_130>",
139
+ "<extra_id_131>",
140
+ "<extra_id_132>",
141
+ "<extra_id_133>",
142
+ "<extra_id_134>",
143
+ "<extra_id_135>",
144
+ "<extra_id_136>",
145
+ "<extra_id_137>",
146
+ "<extra_id_138>",
147
+ "<extra_id_139>",
148
+ "<extra_id_140>",
149
+ "<extra_id_141>",
150
+ "<extra_id_142>",
151
+ "<extra_id_143>",
152
+ "<extra_id_144>",
153
+ "<extra_id_145>",
154
+ "<extra_id_146>",
155
+ "<extra_id_147>",
156
+ "<extra_id_148>",
157
+ "<extra_id_149>",
158
+ "<extra_id_150>",
159
+ "<extra_id_151>",
160
+ "<extra_id_152>",
161
+ "<extra_id_153>",
162
+ "<extra_id_154>",
163
+ "<extra_id_155>",
164
+ "<extra_id_156>",
165
+ "<extra_id_157>",
166
+ "<extra_id_158>",
167
+ "<extra_id_159>",
168
+ "<extra_id_160>",
169
+ "<extra_id_161>",
170
+ "<extra_id_162>",
171
+ "<extra_id_163>",
172
+ "<extra_id_164>",
173
+ "<extra_id_165>",
174
+ "<extra_id_166>",
175
+ "<extra_id_167>",
176
+ "<extra_id_168>",
177
+ "<extra_id_169>",
178
+ "<extra_id_170>",
179
+ "<extra_id_171>",
180
+ "<extra_id_172>",
181
+ "<extra_id_173>",
182
+ "<extra_id_174>",
183
+ "<extra_id_175>",
184
+ "<extra_id_176>",
185
+ "<extra_id_177>",
186
+ "<extra_id_178>",
187
+ "<extra_id_179>",
188
+ "<extra_id_180>",
189
+ "<extra_id_181>",
190
+ "<extra_id_182>",
191
+ "<extra_id_183>",
192
+ "<extra_id_184>",
193
+ "<extra_id_185>",
194
+ "<extra_id_186>",
195
+ "<extra_id_187>",
196
+ "<extra_id_188>",
197
+ "<extra_id_189>",
198
+ "<extra_id_190>",
199
+ "<extra_id_191>",
200
+ "<extra_id_192>",
201
+ "<extra_id_193>",
202
+ "<extra_id_194>",
203
+ "<extra_id_195>",
204
+ "<extra_id_196>",
205
+ "<extra_id_197>",
206
+ "<extra_id_198>",
207
+ "<extra_id_199>",
208
+ "<extra_id_200>",
209
+ "<extra_id_201>",
210
+ "<extra_id_202>",
211
+ "<extra_id_203>",
212
+ "<extra_id_204>",
213
+ "<extra_id_205>",
214
+ "<extra_id_206>",
215
+ "<extra_id_207>",
216
+ "<extra_id_208>",
217
+ "<extra_id_209>",
218
+ "<extra_id_210>",
219
+ "<extra_id_211>",
220
+ "<extra_id_212>",
221
+ "<extra_id_213>",
222
+ "<extra_id_214>",
223
+ "<extra_id_215>",
224
+ "<extra_id_216>",
225
+ "<extra_id_217>",
226
+ "<extra_id_218>",
227
+ "<extra_id_219>",
228
+ "<extra_id_220>",
229
+ "<extra_id_221>",
230
+ "<extra_id_222>",
231
+ "<extra_id_223>",
232
+ "<extra_id_224>",
233
+ "<extra_id_225>",
234
+ "<extra_id_226>",
235
+ "<extra_id_227>",
236
+ "<extra_id_228>",
237
+ "<extra_id_229>",
238
+ "<extra_id_230>",
239
+ "<extra_id_231>",
240
+ "<extra_id_232>",
241
+ "<extra_id_233>",
242
+ "<extra_id_234>",
243
+ "<extra_id_235>",
244
+ "<extra_id_236>",
245
+ "<extra_id_237>",
246
+ "<extra_id_238>",
247
+ "<extra_id_239>",
248
+ "<extra_id_240>",
249
+ "<extra_id_241>",
250
+ "<extra_id_242>",
251
+ "<extra_id_243>",
252
+ "<extra_id_244>",
253
+ "<extra_id_245>",
254
+ "<extra_id_246>",
255
+ "<extra_id_247>",
256
+ "<extra_id_248>",
257
+ "<extra_id_249>",
258
+ "<extra_id_250>",
259
+ "<extra_id_251>",
260
+ "<extra_id_252>",
261
+ "<extra_id_253>",
262
+ "<extra_id_254>",
263
+ "<extra_id_255>",
264
+ "<extra_id_256>",
265
+ "<extra_id_257>",
266
+ "<extra_id_258>",
267
+ "<extra_id_259>",
268
+ "<extra_id_260>",
269
+ "<extra_id_261>",
270
+ "<extra_id_262>",
271
+ "<extra_id_263>",
272
+ "<extra_id_264>",
273
+ "<extra_id_265>",
274
+ "<extra_id_266>",
275
+ "<extra_id_267>",
276
+ "<extra_id_268>",
277
+ "<extra_id_269>",
278
+ "<extra_id_270>",
279
+ "<extra_id_271>",
280
+ "<extra_id_272>",
281
+ "<extra_id_273>",
282
+ "<extra_id_274>",
283
+ "<extra_id_275>",
284
+ "<extra_id_276>",
285
+ "<extra_id_277>",
286
+ "<extra_id_278>",
287
+ "<extra_id_279>",
288
+ "<extra_id_280>",
289
+ "<extra_id_281>",
290
+ "<extra_id_282>",
291
+ "<extra_id_283>",
292
+ "<extra_id_284>",
293
+ "<extra_id_285>",
294
+ "<extra_id_286>",
295
+ "<extra_id_287>",
296
+ "<extra_id_288>",
297
+ "<extra_id_289>",
298
+ "<extra_id_290>",
299
+ "<extra_id_291>",
300
+ "<extra_id_292>",
301
+ "<extra_id_293>",
302
+ "<extra_id_294>",
303
+ "<extra_id_295>",
304
+ "<extra_id_296>",
305
+ "<extra_id_297>",
306
+ "<extra_id_298>",
307
+ "<extra_id_299>"
308
+ ],
309
+ "is_local": true,
310
+ "model_max_length": 1000000000000000019884624838656,
311
+ "model_specific_special_tokens": {},
312
+ "pad_token": "<pad>",
313
+ "sp_model_kwargs": {},
314
+ "spaces_between_special_tokens": false,
315
+ "tokenizer_class": "T5Tokenizer",
316
+ "unk_token": "<unk>"
317
+ }
transformer/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba9f08cfc6b9e245483c0d91ee5088205f7ceaa302f3326c5e29b3c831b02b97
3
+ size 2137450610
transformer/1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b8e7120b9ba90bc1976fd16bdb88b1a09f002f429bc5e8f335845ff10a4a49
3
+ size 2144437513
transformer/2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4867a6c46f7fa1f6dcd2642ae2a7bb9520759bd56a2ed09396266322446d9f
3
+ size 1034389766
transformer/model.safetensors.index.json ADDED
@@ -0,0 +1,1447 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "8",
4
+ "mflux_version": "0.18.6"
5
+ },
6
+ "weight_map": {
7
+ "rope.freqs_cos": "0.safetensors",
8
+ "rope.freqs_sin": "0.safetensors",
9
+ "patch_embedding.weight": "0.safetensors",
10
+ "patch_embedding.bias": "0.safetensors",
11
+ "condition_embedder.time_embedder.linear_1.weight": "0.safetensors",
12
+ "condition_embedder.time_embedder.linear_1.scales": "0.safetensors",
13
+ "condition_embedder.time_embedder.linear_1.biases": "0.safetensors",
14
+ "condition_embedder.time_embedder.linear_1.bias": "0.safetensors",
15
+ "condition_embedder.time_embedder.linear_2.weight": "0.safetensors",
16
+ "condition_embedder.time_embedder.linear_2.scales": "0.safetensors",
17
+ "condition_embedder.time_embedder.linear_2.biases": "0.safetensors",
18
+ "condition_embedder.time_embedder.linear_2.bias": "0.safetensors",
19
+ "condition_embedder.time_proj.weight": "0.safetensors",
20
+ "condition_embedder.time_proj.scales": "0.safetensors",
21
+ "condition_embedder.time_proj.biases": "0.safetensors",
22
+ "condition_embedder.time_proj.bias": "0.safetensors",
23
+ "condition_embedder.text_embedder.linear_1.weight": "0.safetensors",
24
+ "condition_embedder.text_embedder.linear_1.scales": "0.safetensors",
25
+ "condition_embedder.text_embedder.linear_1.biases": "0.safetensors",
26
+ "condition_embedder.text_embedder.linear_1.bias": "0.safetensors",
27
+ "condition_embedder.text_embedder.linear_2.weight": "0.safetensors",
28
+ "condition_embedder.text_embedder.linear_2.scales": "0.safetensors",
29
+ "condition_embedder.text_embedder.linear_2.biases": "0.safetensors",
30
+ "condition_embedder.text_embedder.linear_2.bias": "0.safetensors",
31
+ "blocks.0.attn1.to_q.weight": "0.safetensors",
32
+ "blocks.0.attn1.to_q.scales": "0.safetensors",
33
+ "blocks.0.attn1.to_q.biases": "0.safetensors",
34
+ "blocks.0.attn1.to_q.bias": "0.safetensors",
35
+ "blocks.0.attn1.to_k.weight": "0.safetensors",
36
+ "blocks.0.attn1.to_k.scales": "0.safetensors",
37
+ "blocks.0.attn1.to_k.biases": "0.safetensors",
38
+ "blocks.0.attn1.to_k.bias": "0.safetensors",
39
+ "blocks.0.attn1.to_v.weight": "0.safetensors",
40
+ "blocks.0.attn1.to_v.scales": "0.safetensors",
41
+ "blocks.0.attn1.to_v.biases": "0.safetensors",
42
+ "blocks.0.attn1.to_v.bias": "0.safetensors",
43
+ "blocks.0.attn1.to_out.0.weight": "0.safetensors",
44
+ "blocks.0.attn1.to_out.0.scales": "0.safetensors",
45
+ "blocks.0.attn1.to_out.0.biases": "0.safetensors",
46
+ "blocks.0.attn1.to_out.0.bias": "0.safetensors",
47
+ "blocks.0.attn1.norm_q.weight": "0.safetensors",
48
+ "blocks.0.attn1.norm_k.weight": "0.safetensors",
49
+ "blocks.0.attn2.to_q.weight": "0.safetensors",
50
+ "blocks.0.attn2.to_q.scales": "0.safetensors",
51
+ "blocks.0.attn2.to_q.biases": "0.safetensors",
52
+ "blocks.0.attn2.to_q.bias": "0.safetensors",
53
+ "blocks.0.attn2.to_k.weight": "0.safetensors",
54
+ "blocks.0.attn2.to_k.scales": "0.safetensors",
55
+ "blocks.0.attn2.to_k.biases": "0.safetensors",
56
+ "blocks.0.attn2.to_k.bias": "0.safetensors",
57
+ "blocks.0.attn2.to_v.weight": "0.safetensors",
58
+ "blocks.0.attn2.to_v.scales": "0.safetensors",
59
+ "blocks.0.attn2.to_v.biases": "0.safetensors",
60
+ "blocks.0.attn2.to_v.bias": "0.safetensors",
61
+ "blocks.0.attn2.to_out.0.weight": "0.safetensors",
62
+ "blocks.0.attn2.to_out.0.scales": "0.safetensors",
63
+ "blocks.0.attn2.to_out.0.biases": "0.safetensors",
64
+ "blocks.0.attn2.to_out.0.bias": "0.safetensors",
65
+ "blocks.0.attn2.norm_q.weight": "0.safetensors",
66
+ "blocks.0.attn2.norm_k.weight": "0.safetensors",
67
+ "blocks.0.norm2.weight": "0.safetensors",
68
+ "blocks.0.norm2.bias": "0.safetensors",
69
+ "blocks.0.ffn.net.0.weight": "0.safetensors",
70
+ "blocks.0.ffn.net.0.scales": "0.safetensors",
71
+ "blocks.0.ffn.net.0.biases": "0.safetensors",
72
+ "blocks.0.ffn.net.0.bias": "0.safetensors",
73
+ "blocks.0.ffn.net.1.weight": "0.safetensors",
74
+ "blocks.0.ffn.net.1.scales": "0.safetensors",
75
+ "blocks.0.ffn.net.1.biases": "0.safetensors",
76
+ "blocks.0.ffn.net.1.bias": "0.safetensors",
77
+ "blocks.0.scale_shift_table": "0.safetensors",
78
+ "blocks.1.attn1.to_q.weight": "0.safetensors",
79
+ "blocks.1.attn1.to_q.scales": "0.safetensors",
80
+ "blocks.1.attn1.to_q.biases": "0.safetensors",
81
+ "blocks.1.attn1.to_q.bias": "0.safetensors",
82
+ "blocks.1.attn1.to_k.weight": "0.safetensors",
83
+ "blocks.1.attn1.to_k.scales": "0.safetensors",
84
+ "blocks.1.attn1.to_k.biases": "0.safetensors",
85
+ "blocks.1.attn1.to_k.bias": "0.safetensors",
86
+ "blocks.1.attn1.to_v.weight": "0.safetensors",
87
+ "blocks.1.attn1.to_v.scales": "0.safetensors",
88
+ "blocks.1.attn1.to_v.biases": "0.safetensors",
89
+ "blocks.1.attn1.to_v.bias": "0.safetensors",
90
+ "blocks.1.attn1.to_out.0.weight": "0.safetensors",
91
+ "blocks.1.attn1.to_out.0.scales": "0.safetensors",
92
+ "blocks.1.attn1.to_out.0.biases": "0.safetensors",
93
+ "blocks.1.attn1.to_out.0.bias": "0.safetensors",
94
+ "blocks.1.attn1.norm_q.weight": "0.safetensors",
95
+ "blocks.1.attn1.norm_k.weight": "0.safetensors",
96
+ "blocks.1.attn2.to_q.weight": "0.safetensors",
97
+ "blocks.1.attn2.to_q.scales": "0.safetensors",
98
+ "blocks.1.attn2.to_q.biases": "0.safetensors",
99
+ "blocks.1.attn2.to_q.bias": "0.safetensors",
100
+ "blocks.1.attn2.to_k.weight": "0.safetensors",
101
+ "blocks.1.attn2.to_k.scales": "0.safetensors",
102
+ "blocks.1.attn2.to_k.biases": "0.safetensors",
103
+ "blocks.1.attn2.to_k.bias": "0.safetensors",
104
+ "blocks.1.attn2.to_v.weight": "0.safetensors",
105
+ "blocks.1.attn2.to_v.scales": "0.safetensors",
106
+ "blocks.1.attn2.to_v.biases": "0.safetensors",
107
+ "blocks.1.attn2.to_v.bias": "0.safetensors",
108
+ "blocks.1.attn2.to_out.0.weight": "0.safetensors",
109
+ "blocks.1.attn2.to_out.0.scales": "0.safetensors",
110
+ "blocks.1.attn2.to_out.0.biases": "0.safetensors",
111
+ "blocks.1.attn2.to_out.0.bias": "0.safetensors",
112
+ "blocks.1.attn2.norm_q.weight": "0.safetensors",
113
+ "blocks.1.attn2.norm_k.weight": "0.safetensors",
114
+ "blocks.1.norm2.weight": "0.safetensors",
115
+ "blocks.1.norm2.bias": "0.safetensors",
116
+ "blocks.1.ffn.net.0.weight": "0.safetensors",
117
+ "blocks.1.ffn.net.0.scales": "0.safetensors",
118
+ "blocks.1.ffn.net.0.biases": "0.safetensors",
119
+ "blocks.1.ffn.net.0.bias": "0.safetensors",
120
+ "blocks.1.ffn.net.1.weight": "0.safetensors",
121
+ "blocks.1.ffn.net.1.scales": "0.safetensors",
122
+ "blocks.1.ffn.net.1.biases": "0.safetensors",
123
+ "blocks.1.ffn.net.1.bias": "0.safetensors",
124
+ "blocks.1.scale_shift_table": "0.safetensors",
125
+ "blocks.2.attn1.to_q.weight": "0.safetensors",
126
+ "blocks.2.attn1.to_q.scales": "0.safetensors",
127
+ "blocks.2.attn1.to_q.biases": "0.safetensors",
128
+ "blocks.2.attn1.to_q.bias": "0.safetensors",
129
+ "blocks.2.attn1.to_k.weight": "0.safetensors",
130
+ "blocks.2.attn1.to_k.scales": "0.safetensors",
131
+ "blocks.2.attn1.to_k.biases": "0.safetensors",
132
+ "blocks.2.attn1.to_k.bias": "0.safetensors",
133
+ "blocks.2.attn1.to_v.weight": "0.safetensors",
134
+ "blocks.2.attn1.to_v.scales": "0.safetensors",
135
+ "blocks.2.attn1.to_v.biases": "0.safetensors",
136
+ "blocks.2.attn1.to_v.bias": "0.safetensors",
137
+ "blocks.2.attn1.to_out.0.weight": "0.safetensors",
138
+ "blocks.2.attn1.to_out.0.scales": "0.safetensors",
139
+ "blocks.2.attn1.to_out.0.biases": "0.safetensors",
140
+ "blocks.2.attn1.to_out.0.bias": "0.safetensors",
141
+ "blocks.2.attn1.norm_q.weight": "0.safetensors",
142
+ "blocks.2.attn1.norm_k.weight": "0.safetensors",
143
+ "blocks.2.attn2.to_q.weight": "0.safetensors",
144
+ "blocks.2.attn2.to_q.scales": "0.safetensors",
145
+ "blocks.2.attn2.to_q.biases": "0.safetensors",
146
+ "blocks.2.attn2.to_q.bias": "0.safetensors",
147
+ "blocks.2.attn2.to_k.weight": "0.safetensors",
148
+ "blocks.2.attn2.to_k.scales": "0.safetensors",
149
+ "blocks.2.attn2.to_k.biases": "0.safetensors",
150
+ "blocks.2.attn2.to_k.bias": "0.safetensors",
151
+ "blocks.2.attn2.to_v.weight": "0.safetensors",
152
+ "blocks.2.attn2.to_v.scales": "0.safetensors",
153
+ "blocks.2.attn2.to_v.biases": "0.safetensors",
154
+ "blocks.2.attn2.to_v.bias": "0.safetensors",
155
+ "blocks.2.attn2.to_out.0.weight": "0.safetensors",
156
+ "blocks.2.attn2.to_out.0.scales": "0.safetensors",
157
+ "blocks.2.attn2.to_out.0.biases": "0.safetensors",
158
+ "blocks.2.attn2.to_out.0.bias": "0.safetensors",
159
+ "blocks.2.attn2.norm_q.weight": "0.safetensors",
160
+ "blocks.2.attn2.norm_k.weight": "0.safetensors",
161
+ "blocks.2.norm2.weight": "0.safetensors",
162
+ "blocks.2.norm2.bias": "0.safetensors",
163
+ "blocks.2.ffn.net.0.weight": "0.safetensors",
164
+ "blocks.2.ffn.net.0.scales": "0.safetensors",
165
+ "blocks.2.ffn.net.0.biases": "0.safetensors",
166
+ "blocks.2.ffn.net.0.bias": "0.safetensors",
167
+ "blocks.2.ffn.net.1.weight": "0.safetensors",
168
+ "blocks.2.ffn.net.1.scales": "0.safetensors",
169
+ "blocks.2.ffn.net.1.biases": "0.safetensors",
170
+ "blocks.2.ffn.net.1.bias": "0.safetensors",
171
+ "blocks.2.scale_shift_table": "0.safetensors",
172
+ "blocks.3.attn1.to_q.weight": "0.safetensors",
173
+ "blocks.3.attn1.to_q.scales": "0.safetensors",
174
+ "blocks.3.attn1.to_q.biases": "0.safetensors",
175
+ "blocks.3.attn1.to_q.bias": "0.safetensors",
176
+ "blocks.3.attn1.to_k.weight": "0.safetensors",
177
+ "blocks.3.attn1.to_k.scales": "0.safetensors",
178
+ "blocks.3.attn1.to_k.biases": "0.safetensors",
179
+ "blocks.3.attn1.to_k.bias": "0.safetensors",
180
+ "blocks.3.attn1.to_v.weight": "0.safetensors",
181
+ "blocks.3.attn1.to_v.scales": "0.safetensors",
182
+ "blocks.3.attn1.to_v.biases": "0.safetensors",
183
+ "blocks.3.attn1.to_v.bias": "0.safetensors",
184
+ "blocks.3.attn1.to_out.0.weight": "0.safetensors",
185
+ "blocks.3.attn1.to_out.0.scales": "0.safetensors",
186
+ "blocks.3.attn1.to_out.0.biases": "0.safetensors",
187
+ "blocks.3.attn1.to_out.0.bias": "0.safetensors",
188
+ "blocks.3.attn1.norm_q.weight": "0.safetensors",
189
+ "blocks.3.attn1.norm_k.weight": "0.safetensors",
190
+ "blocks.3.attn2.to_q.weight": "0.safetensors",
191
+ "blocks.3.attn2.to_q.scales": "0.safetensors",
192
+ "blocks.3.attn2.to_q.biases": "0.safetensors",
193
+ "blocks.3.attn2.to_q.bias": "0.safetensors",
194
+ "blocks.3.attn2.to_k.weight": "0.safetensors",
195
+ "blocks.3.attn2.to_k.scales": "0.safetensors",
196
+ "blocks.3.attn2.to_k.biases": "0.safetensors",
197
+ "blocks.3.attn2.to_k.bias": "0.safetensors",
198
+ "blocks.3.attn2.to_v.weight": "0.safetensors",
199
+ "blocks.3.attn2.to_v.scales": "0.safetensors",
200
+ "blocks.3.attn2.to_v.biases": "0.safetensors",
201
+ "blocks.3.attn2.to_v.bias": "0.safetensors",
202
+ "blocks.3.attn2.to_out.0.weight": "0.safetensors",
203
+ "blocks.3.attn2.to_out.0.scales": "0.safetensors",
204
+ "blocks.3.attn2.to_out.0.biases": "0.safetensors",
205
+ "blocks.3.attn2.to_out.0.bias": "0.safetensors",
206
+ "blocks.3.attn2.norm_q.weight": "0.safetensors",
207
+ "blocks.3.attn2.norm_k.weight": "0.safetensors",
208
+ "blocks.3.norm2.weight": "0.safetensors",
209
+ "blocks.3.norm2.bias": "0.safetensors",
210
+ "blocks.3.ffn.net.0.weight": "0.safetensors",
211
+ "blocks.3.ffn.net.0.scales": "0.safetensors",
212
+ "blocks.3.ffn.net.0.biases": "0.safetensors",
213
+ "blocks.3.ffn.net.0.bias": "0.safetensors",
214
+ "blocks.3.ffn.net.1.weight": "0.safetensors",
215
+ "blocks.3.ffn.net.1.scales": "0.safetensors",
216
+ "blocks.3.ffn.net.1.biases": "0.safetensors",
217
+ "blocks.3.ffn.net.1.bias": "0.safetensors",
218
+ "blocks.3.scale_shift_table": "0.safetensors",
219
+ "blocks.4.attn1.to_q.weight": "0.safetensors",
220
+ "blocks.4.attn1.to_q.scales": "0.safetensors",
221
+ "blocks.4.attn1.to_q.biases": "0.safetensors",
222
+ "blocks.4.attn1.to_q.bias": "0.safetensors",
223
+ "blocks.4.attn1.to_k.weight": "0.safetensors",
224
+ "blocks.4.attn1.to_k.scales": "0.safetensors",
225
+ "blocks.4.attn1.to_k.biases": "0.safetensors",
226
+ "blocks.4.attn1.to_k.bias": "0.safetensors",
227
+ "blocks.4.attn1.to_v.weight": "0.safetensors",
228
+ "blocks.4.attn1.to_v.scales": "0.safetensors",
229
+ "blocks.4.attn1.to_v.biases": "0.safetensors",
230
+ "blocks.4.attn1.to_v.bias": "0.safetensors",
231
+ "blocks.4.attn1.to_out.0.weight": "0.safetensors",
232
+ "blocks.4.attn1.to_out.0.scales": "0.safetensors",
233
+ "blocks.4.attn1.to_out.0.biases": "0.safetensors",
234
+ "blocks.4.attn1.to_out.0.bias": "0.safetensors",
235
+ "blocks.4.attn1.norm_q.weight": "0.safetensors",
236
+ "blocks.4.attn1.norm_k.weight": "0.safetensors",
237
+ "blocks.4.attn2.to_q.weight": "0.safetensors",
238
+ "blocks.4.attn2.to_q.scales": "0.safetensors",
239
+ "blocks.4.attn2.to_q.biases": "0.safetensors",
240
+ "blocks.4.attn2.to_q.bias": "0.safetensors",
241
+ "blocks.4.attn2.to_k.weight": "0.safetensors",
242
+ "blocks.4.attn2.to_k.scales": "0.safetensors",
243
+ "blocks.4.attn2.to_k.biases": "0.safetensors",
244
+ "blocks.4.attn2.to_k.bias": "0.safetensors",
245
+ "blocks.4.attn2.to_v.weight": "0.safetensors",
246
+ "blocks.4.attn2.to_v.scales": "0.safetensors",
247
+ "blocks.4.attn2.to_v.biases": "0.safetensors",
248
+ "blocks.4.attn2.to_v.bias": "0.safetensors",
249
+ "blocks.4.attn2.to_out.0.weight": "0.safetensors",
250
+ "blocks.4.attn2.to_out.0.scales": "0.safetensors",
251
+ "blocks.4.attn2.to_out.0.biases": "0.safetensors",
252
+ "blocks.4.attn2.to_out.0.bias": "0.safetensors",
253
+ "blocks.4.attn2.norm_q.weight": "0.safetensors",
254
+ "blocks.4.attn2.norm_k.weight": "0.safetensors",
255
+ "blocks.4.norm2.weight": "0.safetensors",
256
+ "blocks.4.norm2.bias": "0.safetensors",
257
+ "blocks.4.ffn.net.0.weight": "0.safetensors",
258
+ "blocks.4.ffn.net.0.scales": "0.safetensors",
259
+ "blocks.4.ffn.net.0.biases": "0.safetensors",
260
+ "blocks.4.ffn.net.0.bias": "0.safetensors",
261
+ "blocks.4.ffn.net.1.weight": "0.safetensors",
262
+ "blocks.4.ffn.net.1.scales": "0.safetensors",
263
+ "blocks.4.ffn.net.1.biases": "0.safetensors",
264
+ "blocks.4.ffn.net.1.bias": "0.safetensors",
265
+ "blocks.4.scale_shift_table": "0.safetensors",
266
+ "blocks.5.attn1.to_q.weight": "0.safetensors",
267
+ "blocks.5.attn1.to_q.scales": "0.safetensors",
268
+ "blocks.5.attn1.to_q.biases": "0.safetensors",
269
+ "blocks.5.attn1.to_q.bias": "0.safetensors",
270
+ "blocks.5.attn1.to_k.weight": "0.safetensors",
271
+ "blocks.5.attn1.to_k.scales": "0.safetensors",
272
+ "blocks.5.attn1.to_k.biases": "0.safetensors",
273
+ "blocks.5.attn1.to_k.bias": "0.safetensors",
274
+ "blocks.5.attn1.to_v.weight": "0.safetensors",
275
+ "blocks.5.attn1.to_v.scales": "0.safetensors",
276
+ "blocks.5.attn1.to_v.biases": "0.safetensors",
277
+ "blocks.5.attn1.to_v.bias": "0.safetensors",
278
+ "blocks.5.attn1.to_out.0.weight": "0.safetensors",
279
+ "blocks.5.attn1.to_out.0.scales": "0.safetensors",
280
+ "blocks.5.attn1.to_out.0.biases": "0.safetensors",
281
+ "blocks.5.attn1.to_out.0.bias": "0.safetensors",
282
+ "blocks.5.attn1.norm_q.weight": "0.safetensors",
283
+ "blocks.5.attn1.norm_k.weight": "0.safetensors",
284
+ "blocks.5.attn2.to_q.weight": "0.safetensors",
285
+ "blocks.5.attn2.to_q.scales": "0.safetensors",
286
+ "blocks.5.attn2.to_q.biases": "0.safetensors",
287
+ "blocks.5.attn2.to_q.bias": "0.safetensors",
288
+ "blocks.5.attn2.to_k.weight": "0.safetensors",
289
+ "blocks.5.attn2.to_k.scales": "0.safetensors",
290
+ "blocks.5.attn2.to_k.biases": "0.safetensors",
291
+ "blocks.5.attn2.to_k.bias": "0.safetensors",
292
+ "blocks.5.attn2.to_v.weight": "0.safetensors",
293
+ "blocks.5.attn2.to_v.scales": "0.safetensors",
294
+ "blocks.5.attn2.to_v.biases": "0.safetensors",
295
+ "blocks.5.attn2.to_v.bias": "0.safetensors",
296
+ "blocks.5.attn2.to_out.0.weight": "0.safetensors",
297
+ "blocks.5.attn2.to_out.0.scales": "0.safetensors",
298
+ "blocks.5.attn2.to_out.0.biases": "0.safetensors",
299
+ "blocks.5.attn2.to_out.0.bias": "0.safetensors",
300
+ "blocks.5.attn2.norm_q.weight": "0.safetensors",
301
+ "blocks.5.attn2.norm_k.weight": "0.safetensors",
302
+ "blocks.5.norm2.weight": "0.safetensors",
303
+ "blocks.5.norm2.bias": "0.safetensors",
304
+ "blocks.5.ffn.net.0.weight": "0.safetensors",
305
+ "blocks.5.ffn.net.0.scales": "0.safetensors",
306
+ "blocks.5.ffn.net.0.biases": "0.safetensors",
307
+ "blocks.5.ffn.net.0.bias": "0.safetensors",
308
+ "blocks.5.ffn.net.1.weight": "0.safetensors",
309
+ "blocks.5.ffn.net.1.scales": "0.safetensors",
310
+ "blocks.5.ffn.net.1.biases": "0.safetensors",
311
+ "blocks.5.ffn.net.1.bias": "0.safetensors",
312
+ "blocks.5.scale_shift_table": "0.safetensors",
313
+ "blocks.6.attn1.to_q.weight": "0.safetensors",
314
+ "blocks.6.attn1.to_q.scales": "0.safetensors",
315
+ "blocks.6.attn1.to_q.biases": "0.safetensors",
316
+ "blocks.6.attn1.to_q.bias": "0.safetensors",
317
+ "blocks.6.attn1.to_k.weight": "0.safetensors",
318
+ "blocks.6.attn1.to_k.scales": "0.safetensors",
319
+ "blocks.6.attn1.to_k.biases": "0.safetensors",
320
+ "blocks.6.attn1.to_k.bias": "0.safetensors",
321
+ "blocks.6.attn1.to_v.weight": "0.safetensors",
322
+ "blocks.6.attn1.to_v.scales": "0.safetensors",
323
+ "blocks.6.attn1.to_v.biases": "0.safetensors",
324
+ "blocks.6.attn1.to_v.bias": "0.safetensors",
325
+ "blocks.6.attn1.to_out.0.weight": "0.safetensors",
326
+ "blocks.6.attn1.to_out.0.scales": "0.safetensors",
327
+ "blocks.6.attn1.to_out.0.biases": "0.safetensors",
328
+ "blocks.6.attn1.to_out.0.bias": "0.safetensors",
329
+ "blocks.6.attn1.norm_q.weight": "0.safetensors",
330
+ "blocks.6.attn1.norm_k.weight": "0.safetensors",
331
+ "blocks.6.attn2.to_q.weight": "0.safetensors",
332
+ "blocks.6.attn2.to_q.scales": "0.safetensors",
333
+ "blocks.6.attn2.to_q.biases": "0.safetensors",
334
+ "blocks.6.attn2.to_q.bias": "0.safetensors",
335
+ "blocks.6.attn2.to_k.weight": "0.safetensors",
336
+ "blocks.6.attn2.to_k.scales": "0.safetensors",
337
+ "blocks.6.attn2.to_k.biases": "0.safetensors",
338
+ "blocks.6.attn2.to_k.bias": "0.safetensors",
339
+ "blocks.6.attn2.to_v.weight": "0.safetensors",
340
+ "blocks.6.attn2.to_v.scales": "0.safetensors",
341
+ "blocks.6.attn2.to_v.biases": "0.safetensors",
342
+ "blocks.6.attn2.to_v.bias": "0.safetensors",
343
+ "blocks.6.attn2.to_out.0.weight": "0.safetensors",
344
+ "blocks.6.attn2.to_out.0.scales": "0.safetensors",
345
+ "blocks.6.attn2.to_out.0.biases": "0.safetensors",
346
+ "blocks.6.attn2.to_out.0.bias": "0.safetensors",
347
+ "blocks.6.attn2.norm_q.weight": "0.safetensors",
348
+ "blocks.6.attn2.norm_k.weight": "0.safetensors",
349
+ "blocks.6.norm2.weight": "0.safetensors",
350
+ "blocks.6.norm2.bias": "0.safetensors",
351
+ "blocks.6.ffn.net.0.weight": "0.safetensors",
352
+ "blocks.6.ffn.net.0.scales": "0.safetensors",
353
+ "blocks.6.ffn.net.0.biases": "0.safetensors",
354
+ "blocks.6.ffn.net.0.bias": "0.safetensors",
355
+ "blocks.6.ffn.net.1.weight": "0.safetensors",
356
+ "blocks.6.ffn.net.1.scales": "0.safetensors",
357
+ "blocks.6.ffn.net.1.biases": "0.safetensors",
358
+ "blocks.6.ffn.net.1.bias": "0.safetensors",
359
+ "blocks.6.scale_shift_table": "0.safetensors",
360
+ "blocks.7.attn1.to_q.weight": "0.safetensors",
361
+ "blocks.7.attn1.to_q.scales": "0.safetensors",
362
+ "blocks.7.attn1.to_q.biases": "0.safetensors",
363
+ "blocks.7.attn1.to_q.bias": "0.safetensors",
364
+ "blocks.7.attn1.to_k.weight": "0.safetensors",
365
+ "blocks.7.attn1.to_k.scales": "0.safetensors",
366
+ "blocks.7.attn1.to_k.biases": "0.safetensors",
367
+ "blocks.7.attn1.to_k.bias": "0.safetensors",
368
+ "blocks.7.attn1.to_v.weight": "0.safetensors",
369
+ "blocks.7.attn1.to_v.scales": "0.safetensors",
370
+ "blocks.7.attn1.to_v.biases": "0.safetensors",
371
+ "blocks.7.attn1.to_v.bias": "0.safetensors",
372
+ "blocks.7.attn1.to_out.0.weight": "0.safetensors",
373
+ "blocks.7.attn1.to_out.0.scales": "0.safetensors",
374
+ "blocks.7.attn1.to_out.0.biases": "0.safetensors",
375
+ "blocks.7.attn1.to_out.0.bias": "0.safetensors",
376
+ "blocks.7.attn1.norm_q.weight": "0.safetensors",
377
+ "blocks.7.attn1.norm_k.weight": "0.safetensors",
378
+ "blocks.7.attn2.to_q.weight": "0.safetensors",
379
+ "blocks.7.attn2.to_q.scales": "0.safetensors",
380
+ "blocks.7.attn2.to_q.biases": "0.safetensors",
381
+ "blocks.7.attn2.to_q.bias": "0.safetensors",
382
+ "blocks.7.attn2.to_k.weight": "0.safetensors",
383
+ "blocks.7.attn2.to_k.scales": "0.safetensors",
384
+ "blocks.7.attn2.to_k.biases": "0.safetensors",
385
+ "blocks.7.attn2.to_k.bias": "0.safetensors",
386
+ "blocks.7.attn2.to_v.weight": "0.safetensors",
387
+ "blocks.7.attn2.to_v.scales": "0.safetensors",
388
+ "blocks.7.attn2.to_v.biases": "0.safetensors",
389
+ "blocks.7.attn2.to_v.bias": "0.safetensors",
390
+ "blocks.7.attn2.to_out.0.weight": "0.safetensors",
391
+ "blocks.7.attn2.to_out.0.scales": "0.safetensors",
392
+ "blocks.7.attn2.to_out.0.biases": "0.safetensors",
393
+ "blocks.7.attn2.to_out.0.bias": "0.safetensors",
394
+ "blocks.7.attn2.norm_q.weight": "0.safetensors",
395
+ "blocks.7.attn2.norm_k.weight": "0.safetensors",
396
+ "blocks.7.norm2.weight": "0.safetensors",
397
+ "blocks.7.norm2.bias": "0.safetensors",
398
+ "blocks.7.ffn.net.0.weight": "0.safetensors",
399
+ "blocks.7.ffn.net.0.scales": "0.safetensors",
400
+ "blocks.7.ffn.net.0.biases": "0.safetensors",
401
+ "blocks.7.ffn.net.0.bias": "0.safetensors",
402
+ "blocks.7.ffn.net.1.weight": "0.safetensors",
403
+ "blocks.7.ffn.net.1.scales": "0.safetensors",
404
+ "blocks.7.ffn.net.1.biases": "0.safetensors",
405
+ "blocks.7.ffn.net.1.bias": "0.safetensors",
406
+ "blocks.7.scale_shift_table": "0.safetensors",
407
+ "blocks.8.attn1.to_q.weight": "0.safetensors",
408
+ "blocks.8.attn1.to_q.scales": "0.safetensors",
409
+ "blocks.8.attn1.to_q.biases": "0.safetensors",
410
+ "blocks.8.attn1.to_q.bias": "0.safetensors",
411
+ "blocks.8.attn1.to_k.weight": "0.safetensors",
412
+ "blocks.8.attn1.to_k.scales": "0.safetensors",
413
+ "blocks.8.attn1.to_k.biases": "0.safetensors",
414
+ "blocks.8.attn1.to_k.bias": "0.safetensors",
415
+ "blocks.8.attn1.to_v.weight": "0.safetensors",
416
+ "blocks.8.attn1.to_v.scales": "0.safetensors",
417
+ "blocks.8.attn1.to_v.biases": "0.safetensors",
418
+ "blocks.8.attn1.to_v.bias": "0.safetensors",
419
+ "blocks.8.attn1.to_out.0.weight": "0.safetensors",
420
+ "blocks.8.attn1.to_out.0.scales": "0.safetensors",
421
+ "blocks.8.attn1.to_out.0.biases": "0.safetensors",
422
+ "blocks.8.attn1.to_out.0.bias": "0.safetensors",
423
+ "blocks.8.attn1.norm_q.weight": "0.safetensors",
424
+ "blocks.8.attn1.norm_k.weight": "0.safetensors",
425
+ "blocks.8.attn2.to_q.weight": "0.safetensors",
426
+ "blocks.8.attn2.to_q.scales": "0.safetensors",
427
+ "blocks.8.attn2.to_q.biases": "0.safetensors",
428
+ "blocks.8.attn2.to_q.bias": "0.safetensors",
429
+ "blocks.8.attn2.to_k.weight": "0.safetensors",
430
+ "blocks.8.attn2.to_k.scales": "0.safetensors",
431
+ "blocks.8.attn2.to_k.biases": "0.safetensors",
432
+ "blocks.8.attn2.to_k.bias": "0.safetensors",
433
+ "blocks.8.attn2.to_v.weight": "0.safetensors",
434
+ "blocks.8.attn2.to_v.scales": "0.safetensors",
435
+ "blocks.8.attn2.to_v.biases": "0.safetensors",
436
+ "blocks.8.attn2.to_v.bias": "0.safetensors",
437
+ "blocks.8.attn2.to_out.0.weight": "0.safetensors",
438
+ "blocks.8.attn2.to_out.0.scales": "0.safetensors",
439
+ "blocks.8.attn2.to_out.0.biases": "0.safetensors",
440
+ "blocks.8.attn2.to_out.0.bias": "0.safetensors",
441
+ "blocks.8.attn2.norm_q.weight": "0.safetensors",
442
+ "blocks.8.attn2.norm_k.weight": "0.safetensors",
443
+ "blocks.8.norm2.weight": "0.safetensors",
444
+ "blocks.8.norm2.bias": "0.safetensors",
445
+ "blocks.8.ffn.net.0.weight": "0.safetensors",
446
+ "blocks.8.ffn.net.0.scales": "0.safetensors",
447
+ "blocks.8.ffn.net.0.biases": "0.safetensors",
448
+ "blocks.8.ffn.net.0.bias": "0.safetensors",
449
+ "blocks.8.ffn.net.1.weight": "0.safetensors",
450
+ "blocks.8.ffn.net.1.scales": "0.safetensors",
451
+ "blocks.8.ffn.net.1.biases": "0.safetensors",
452
+ "blocks.8.ffn.net.1.bias": "0.safetensors",
453
+ "blocks.8.scale_shift_table": "0.safetensors",
454
+ "blocks.9.attn1.to_q.weight": "0.safetensors",
455
+ "blocks.9.attn1.to_q.scales": "0.safetensors",
456
+ "blocks.9.attn1.to_q.biases": "0.safetensors",
457
+ "blocks.9.attn1.to_q.bias": "0.safetensors",
458
+ "blocks.9.attn1.to_k.weight": "0.safetensors",
459
+ "blocks.9.attn1.to_k.scales": "0.safetensors",
460
+ "blocks.9.attn1.to_k.biases": "0.safetensors",
461
+ "blocks.9.attn1.to_k.bias": "0.safetensors",
462
+ "blocks.9.attn1.to_v.weight": "0.safetensors",
463
+ "blocks.9.attn1.to_v.scales": "0.safetensors",
464
+ "blocks.9.attn1.to_v.biases": "0.safetensors",
465
+ "blocks.9.attn1.to_v.bias": "0.safetensors",
466
+ "blocks.9.attn1.to_out.0.weight": "0.safetensors",
467
+ "blocks.9.attn1.to_out.0.scales": "0.safetensors",
468
+ "blocks.9.attn1.to_out.0.biases": "0.safetensors",
469
+ "blocks.9.attn1.to_out.0.bias": "0.safetensors",
470
+ "blocks.9.attn1.norm_q.weight": "0.safetensors",
471
+ "blocks.9.attn1.norm_k.weight": "0.safetensors",
472
+ "blocks.9.attn2.to_q.weight": "0.safetensors",
473
+ "blocks.9.attn2.to_q.scales": "0.safetensors",
474
+ "blocks.9.attn2.to_q.biases": "0.safetensors",
475
+ "blocks.9.attn2.to_q.bias": "0.safetensors",
476
+ "blocks.9.attn2.to_k.weight": "0.safetensors",
477
+ "blocks.9.attn2.to_k.scales": "0.safetensors",
478
+ "blocks.9.attn2.to_k.biases": "0.safetensors",
479
+ "blocks.9.attn2.to_k.bias": "0.safetensors",
480
+ "blocks.9.attn2.to_v.weight": "0.safetensors",
481
+ "blocks.9.attn2.to_v.scales": "0.safetensors",
482
+ "blocks.9.attn2.to_v.biases": "0.safetensors",
483
+ "blocks.9.attn2.to_v.bias": "0.safetensors",
484
+ "blocks.9.attn2.to_out.0.weight": "0.safetensors",
485
+ "blocks.9.attn2.to_out.0.scales": "0.safetensors",
486
+ "blocks.9.attn2.to_out.0.biases": "0.safetensors",
487
+ "blocks.9.attn2.to_out.0.bias": "0.safetensors",
488
+ "blocks.9.attn2.norm_q.weight": "0.safetensors",
489
+ "blocks.9.attn2.norm_k.weight": "0.safetensors",
490
+ "blocks.9.norm2.weight": "0.safetensors",
491
+ "blocks.9.norm2.bias": "0.safetensors",
492
+ "blocks.9.ffn.net.0.weight": "0.safetensors",
493
+ "blocks.9.ffn.net.0.scales": "0.safetensors",
494
+ "blocks.9.ffn.net.0.biases": "0.safetensors",
495
+ "blocks.9.ffn.net.0.bias": "0.safetensors",
496
+ "blocks.9.ffn.net.1.weight": "0.safetensors",
497
+ "blocks.9.ffn.net.1.scales": "0.safetensors",
498
+ "blocks.9.ffn.net.1.biases": "0.safetensors",
499
+ "blocks.9.ffn.net.1.bias": "0.safetensors",
500
+ "blocks.9.scale_shift_table": "0.safetensors",
501
+ "blocks.10.attn1.to_q.weight": "0.safetensors",
502
+ "blocks.10.attn1.to_q.scales": "0.safetensors",
503
+ "blocks.10.attn1.to_q.biases": "0.safetensors",
504
+ "blocks.10.attn1.to_q.bias": "0.safetensors",
505
+ "blocks.10.attn1.to_k.weight": "0.safetensors",
506
+ "blocks.10.attn1.to_k.scales": "0.safetensors",
507
+ "blocks.10.attn1.to_k.biases": "0.safetensors",
508
+ "blocks.10.attn1.to_k.bias": "0.safetensors",
509
+ "blocks.10.attn1.to_v.weight": "0.safetensors",
510
+ "blocks.10.attn1.to_v.scales": "0.safetensors",
511
+ "blocks.10.attn1.to_v.biases": "0.safetensors",
512
+ "blocks.10.attn1.to_v.bias": "0.safetensors",
513
+ "blocks.10.attn1.to_out.0.weight": "0.safetensors",
514
+ "blocks.10.attn1.to_out.0.scales": "0.safetensors",
515
+ "blocks.10.attn1.to_out.0.biases": "0.safetensors",
516
+ "blocks.10.attn1.to_out.0.bias": "0.safetensors",
517
+ "blocks.10.attn1.norm_q.weight": "0.safetensors",
518
+ "blocks.10.attn1.norm_k.weight": "0.safetensors",
519
+ "blocks.10.attn2.to_q.weight": "0.safetensors",
520
+ "blocks.10.attn2.to_q.scales": "0.safetensors",
521
+ "blocks.10.attn2.to_q.biases": "0.safetensors",
522
+ "blocks.10.attn2.to_q.bias": "0.safetensors",
523
+ "blocks.10.attn2.to_k.weight": "0.safetensors",
524
+ "blocks.10.attn2.to_k.scales": "0.safetensors",
525
+ "blocks.10.attn2.to_k.biases": "0.safetensors",
526
+ "blocks.10.attn2.to_k.bias": "0.safetensors",
527
+ "blocks.10.attn2.to_v.weight": "0.safetensors",
528
+ "blocks.10.attn2.to_v.scales": "0.safetensors",
529
+ "blocks.10.attn2.to_v.biases": "0.safetensors",
530
+ "blocks.10.attn2.to_v.bias": "0.safetensors",
531
+ "blocks.10.attn2.to_out.0.weight": "0.safetensors",
532
+ "blocks.10.attn2.to_out.0.scales": "0.safetensors",
533
+ "blocks.10.attn2.to_out.0.biases": "0.safetensors",
534
+ "blocks.10.attn2.to_out.0.bias": "0.safetensors",
535
+ "blocks.10.attn2.norm_q.weight": "0.safetensors",
536
+ "blocks.10.attn2.norm_k.weight": "0.safetensors",
537
+ "blocks.10.norm2.weight": "0.safetensors",
538
+ "blocks.10.norm2.bias": "0.safetensors",
539
+ "blocks.10.ffn.net.0.weight": "0.safetensors",
540
+ "blocks.10.ffn.net.0.scales": "0.safetensors",
541
+ "blocks.10.ffn.net.0.biases": "0.safetensors",
542
+ "blocks.10.ffn.net.0.bias": "0.safetensors",
543
+ "blocks.10.ffn.net.1.weight": "0.safetensors",
544
+ "blocks.10.ffn.net.1.scales": "0.safetensors",
545
+ "blocks.10.ffn.net.1.biases": "0.safetensors",
546
+ "blocks.10.ffn.net.1.bias": "0.safetensors",
547
+ "blocks.10.scale_shift_table": "0.safetensors",
548
+ "blocks.11.attn1.to_q.weight": "0.safetensors",
549
+ "blocks.11.attn1.to_q.scales": "0.safetensors",
550
+ "blocks.11.attn1.to_q.biases": "0.safetensors",
551
+ "blocks.11.attn1.to_q.bias": "0.safetensors",
552
+ "blocks.11.attn1.to_k.weight": "0.safetensors",
553
+ "blocks.11.attn1.to_k.scales": "0.safetensors",
554
+ "blocks.11.attn1.to_k.biases": "0.safetensors",
555
+ "blocks.11.attn1.to_k.bias": "0.safetensors",
556
+ "blocks.11.attn1.to_v.weight": "0.safetensors",
557
+ "blocks.11.attn1.to_v.scales": "0.safetensors",
558
+ "blocks.11.attn1.to_v.biases": "0.safetensors",
559
+ "blocks.11.attn1.to_v.bias": "0.safetensors",
560
+ "blocks.11.attn1.to_out.0.weight": "0.safetensors",
561
+ "blocks.11.attn1.to_out.0.scales": "0.safetensors",
562
+ "blocks.11.attn1.to_out.0.biases": "0.safetensors",
563
+ "blocks.11.attn1.to_out.0.bias": "0.safetensors",
564
+ "blocks.11.attn1.norm_q.weight": "0.safetensors",
565
+ "blocks.11.attn1.norm_k.weight": "0.safetensors",
566
+ "blocks.11.attn2.to_q.weight": "0.safetensors",
567
+ "blocks.11.attn2.to_q.scales": "0.safetensors",
568
+ "blocks.11.attn2.to_q.biases": "0.safetensors",
569
+ "blocks.11.attn2.to_q.bias": "0.safetensors",
570
+ "blocks.11.attn2.to_k.weight": "0.safetensors",
571
+ "blocks.11.attn2.to_k.scales": "0.safetensors",
572
+ "blocks.11.attn2.to_k.biases": "0.safetensors",
573
+ "blocks.11.attn2.to_k.bias": "0.safetensors",
574
+ "blocks.11.attn2.to_v.weight": "0.safetensors",
575
+ "blocks.11.attn2.to_v.scales": "0.safetensors",
576
+ "blocks.11.attn2.to_v.biases": "0.safetensors",
577
+ "blocks.11.attn2.to_v.bias": "0.safetensors",
578
+ "blocks.11.attn2.to_out.0.weight": "0.safetensors",
579
+ "blocks.11.attn2.to_out.0.scales": "0.safetensors",
580
+ "blocks.11.attn2.to_out.0.biases": "0.safetensors",
581
+ "blocks.11.attn2.to_out.0.bias": "0.safetensors",
582
+ "blocks.11.attn2.norm_q.weight": "0.safetensors",
583
+ "blocks.11.attn2.norm_k.weight": "0.safetensors",
584
+ "blocks.11.norm2.weight": "0.safetensors",
585
+ "blocks.11.norm2.bias": "0.safetensors",
586
+ "blocks.11.ffn.net.0.weight": "0.safetensors",
587
+ "blocks.11.ffn.net.0.scales": "0.safetensors",
588
+ "blocks.11.ffn.net.0.biases": "0.safetensors",
589
+ "blocks.11.ffn.net.0.bias": "0.safetensors",
590
+ "blocks.11.ffn.net.1.weight": "1.safetensors",
591
+ "blocks.11.ffn.net.1.scales": "1.safetensors",
592
+ "blocks.11.ffn.net.1.biases": "1.safetensors",
593
+ "blocks.11.ffn.net.1.bias": "1.safetensors",
594
+ "blocks.11.scale_shift_table": "1.safetensors",
595
+ "blocks.12.attn1.to_q.weight": "1.safetensors",
596
+ "blocks.12.attn1.to_q.scales": "1.safetensors",
597
+ "blocks.12.attn1.to_q.biases": "1.safetensors",
598
+ "blocks.12.attn1.to_q.bias": "1.safetensors",
599
+ "blocks.12.attn1.to_k.weight": "1.safetensors",
600
+ "blocks.12.attn1.to_k.scales": "1.safetensors",
601
+ "blocks.12.attn1.to_k.biases": "1.safetensors",
602
+ "blocks.12.attn1.to_k.bias": "1.safetensors",
603
+ "blocks.12.attn1.to_v.weight": "1.safetensors",
604
+ "blocks.12.attn1.to_v.scales": "1.safetensors",
605
+ "blocks.12.attn1.to_v.biases": "1.safetensors",
606
+ "blocks.12.attn1.to_v.bias": "1.safetensors",
607
+ "blocks.12.attn1.to_out.0.weight": "1.safetensors",
608
+ "blocks.12.attn1.to_out.0.scales": "1.safetensors",
609
+ "blocks.12.attn1.to_out.0.biases": "1.safetensors",
610
+ "blocks.12.attn1.to_out.0.bias": "1.safetensors",
611
+ "blocks.12.attn1.norm_q.weight": "1.safetensors",
612
+ "blocks.12.attn1.norm_k.weight": "1.safetensors",
613
+ "blocks.12.attn2.to_q.weight": "1.safetensors",
614
+ "blocks.12.attn2.to_q.scales": "1.safetensors",
615
+ "blocks.12.attn2.to_q.biases": "1.safetensors",
616
+ "blocks.12.attn2.to_q.bias": "1.safetensors",
617
+ "blocks.12.attn2.to_k.weight": "1.safetensors",
618
+ "blocks.12.attn2.to_k.scales": "1.safetensors",
619
+ "blocks.12.attn2.to_k.biases": "1.safetensors",
620
+ "blocks.12.attn2.to_k.bias": "1.safetensors",
621
+ "blocks.12.attn2.to_v.weight": "1.safetensors",
622
+ "blocks.12.attn2.to_v.scales": "1.safetensors",
623
+ "blocks.12.attn2.to_v.biases": "1.safetensors",
624
+ "blocks.12.attn2.to_v.bias": "1.safetensors",
625
+ "blocks.12.attn2.to_out.0.weight": "1.safetensors",
626
+ "blocks.12.attn2.to_out.0.scales": "1.safetensors",
627
+ "blocks.12.attn2.to_out.0.biases": "1.safetensors",
628
+ "blocks.12.attn2.to_out.0.bias": "1.safetensors",
629
+ "blocks.12.attn2.norm_q.weight": "1.safetensors",
630
+ "blocks.12.attn2.norm_k.weight": "1.safetensors",
631
+ "blocks.12.norm2.weight": "1.safetensors",
632
+ "blocks.12.norm2.bias": "1.safetensors",
633
+ "blocks.12.ffn.net.0.weight": "1.safetensors",
634
+ "blocks.12.ffn.net.0.scales": "1.safetensors",
635
+ "blocks.12.ffn.net.0.biases": "1.safetensors",
636
+ "blocks.12.ffn.net.0.bias": "1.safetensors",
637
+ "blocks.12.ffn.net.1.weight": "1.safetensors",
638
+ "blocks.12.ffn.net.1.scales": "1.safetensors",
639
+ "blocks.12.ffn.net.1.biases": "1.safetensors",
640
+ "blocks.12.ffn.net.1.bias": "1.safetensors",
641
+ "blocks.12.scale_shift_table": "1.safetensors",
642
+ "blocks.13.attn1.to_q.weight": "1.safetensors",
643
+ "blocks.13.attn1.to_q.scales": "1.safetensors",
644
+ "blocks.13.attn1.to_q.biases": "1.safetensors",
645
+ "blocks.13.attn1.to_q.bias": "1.safetensors",
646
+ "blocks.13.attn1.to_k.weight": "1.safetensors",
647
+ "blocks.13.attn1.to_k.scales": "1.safetensors",
648
+ "blocks.13.attn1.to_k.biases": "1.safetensors",
649
+ "blocks.13.attn1.to_k.bias": "1.safetensors",
650
+ "blocks.13.attn1.to_v.weight": "1.safetensors",
651
+ "blocks.13.attn1.to_v.scales": "1.safetensors",
652
+ "blocks.13.attn1.to_v.biases": "1.safetensors",
653
+ "blocks.13.attn1.to_v.bias": "1.safetensors",
654
+ "blocks.13.attn1.to_out.0.weight": "1.safetensors",
655
+ "blocks.13.attn1.to_out.0.scales": "1.safetensors",
656
+ "blocks.13.attn1.to_out.0.biases": "1.safetensors",
657
+ "blocks.13.attn1.to_out.0.bias": "1.safetensors",
658
+ "blocks.13.attn1.norm_q.weight": "1.safetensors",
659
+ "blocks.13.attn1.norm_k.weight": "1.safetensors",
660
+ "blocks.13.attn2.to_q.weight": "1.safetensors",
661
+ "blocks.13.attn2.to_q.scales": "1.safetensors",
662
+ "blocks.13.attn2.to_q.biases": "1.safetensors",
663
+ "blocks.13.attn2.to_q.bias": "1.safetensors",
664
+ "blocks.13.attn2.to_k.weight": "1.safetensors",
665
+ "blocks.13.attn2.to_k.scales": "1.safetensors",
666
+ "blocks.13.attn2.to_k.biases": "1.safetensors",
667
+ "blocks.13.attn2.to_k.bias": "1.safetensors",
668
+ "blocks.13.attn2.to_v.weight": "1.safetensors",
669
+ "blocks.13.attn2.to_v.scales": "1.safetensors",
670
+ "blocks.13.attn2.to_v.biases": "1.safetensors",
671
+ "blocks.13.attn2.to_v.bias": "1.safetensors",
672
+ "blocks.13.attn2.to_out.0.weight": "1.safetensors",
673
+ "blocks.13.attn2.to_out.0.scales": "1.safetensors",
674
+ "blocks.13.attn2.to_out.0.biases": "1.safetensors",
675
+ "blocks.13.attn2.to_out.0.bias": "1.safetensors",
676
+ "blocks.13.attn2.norm_q.weight": "1.safetensors",
677
+ "blocks.13.attn2.norm_k.weight": "1.safetensors",
678
+ "blocks.13.norm2.weight": "1.safetensors",
679
+ "blocks.13.norm2.bias": "1.safetensors",
680
+ "blocks.13.ffn.net.0.weight": "1.safetensors",
681
+ "blocks.13.ffn.net.0.scales": "1.safetensors",
682
+ "blocks.13.ffn.net.0.biases": "1.safetensors",
683
+ "blocks.13.ffn.net.0.bias": "1.safetensors",
684
+ "blocks.13.ffn.net.1.weight": "1.safetensors",
685
+ "blocks.13.ffn.net.1.scales": "1.safetensors",
686
+ "blocks.13.ffn.net.1.biases": "1.safetensors",
687
+ "blocks.13.ffn.net.1.bias": "1.safetensors",
688
+ "blocks.13.scale_shift_table": "1.safetensors",
689
+ "blocks.14.attn1.to_q.weight": "1.safetensors",
690
+ "blocks.14.attn1.to_q.scales": "1.safetensors",
691
+ "blocks.14.attn1.to_q.biases": "1.safetensors",
692
+ "blocks.14.attn1.to_q.bias": "1.safetensors",
693
+ "blocks.14.attn1.to_k.weight": "1.safetensors",
694
+ "blocks.14.attn1.to_k.scales": "1.safetensors",
695
+ "blocks.14.attn1.to_k.biases": "1.safetensors",
696
+ "blocks.14.attn1.to_k.bias": "1.safetensors",
697
+ "blocks.14.attn1.to_v.weight": "1.safetensors",
698
+ "blocks.14.attn1.to_v.scales": "1.safetensors",
699
+ "blocks.14.attn1.to_v.biases": "1.safetensors",
700
+ "blocks.14.attn1.to_v.bias": "1.safetensors",
701
+ "blocks.14.attn1.to_out.0.weight": "1.safetensors",
702
+ "blocks.14.attn1.to_out.0.scales": "1.safetensors",
703
+ "blocks.14.attn1.to_out.0.biases": "1.safetensors",
704
+ "blocks.14.attn1.to_out.0.bias": "1.safetensors",
705
+ "blocks.14.attn1.norm_q.weight": "1.safetensors",
706
+ "blocks.14.attn1.norm_k.weight": "1.safetensors",
707
+ "blocks.14.attn2.to_q.weight": "1.safetensors",
708
+ "blocks.14.attn2.to_q.scales": "1.safetensors",
709
+ "blocks.14.attn2.to_q.biases": "1.safetensors",
710
+ "blocks.14.attn2.to_q.bias": "1.safetensors",
711
+ "blocks.14.attn2.to_k.weight": "1.safetensors",
712
+ "blocks.14.attn2.to_k.scales": "1.safetensors",
713
+ "blocks.14.attn2.to_k.biases": "1.safetensors",
714
+ "blocks.14.attn2.to_k.bias": "1.safetensors",
715
+ "blocks.14.attn2.to_v.weight": "1.safetensors",
716
+ "blocks.14.attn2.to_v.scales": "1.safetensors",
717
+ "blocks.14.attn2.to_v.biases": "1.safetensors",
718
+ "blocks.14.attn2.to_v.bias": "1.safetensors",
719
+ "blocks.14.attn2.to_out.0.weight": "1.safetensors",
720
+ "blocks.14.attn2.to_out.0.scales": "1.safetensors",
721
+ "blocks.14.attn2.to_out.0.biases": "1.safetensors",
722
+ "blocks.14.attn2.to_out.0.bias": "1.safetensors",
723
+ "blocks.14.attn2.norm_q.weight": "1.safetensors",
724
+ "blocks.14.attn2.norm_k.weight": "1.safetensors",
725
+ "blocks.14.norm2.weight": "1.safetensors",
726
+ "blocks.14.norm2.bias": "1.safetensors",
727
+ "blocks.14.ffn.net.0.weight": "1.safetensors",
728
+ "blocks.14.ffn.net.0.scales": "1.safetensors",
729
+ "blocks.14.ffn.net.0.biases": "1.safetensors",
730
+ "blocks.14.ffn.net.0.bias": "1.safetensors",
731
+ "blocks.14.ffn.net.1.weight": "1.safetensors",
732
+ "blocks.14.ffn.net.1.scales": "1.safetensors",
733
+ "blocks.14.ffn.net.1.biases": "1.safetensors",
734
+ "blocks.14.ffn.net.1.bias": "1.safetensors",
735
+ "blocks.14.scale_shift_table": "1.safetensors",
736
+ "blocks.15.attn1.to_q.weight": "1.safetensors",
737
+ "blocks.15.attn1.to_q.scales": "1.safetensors",
738
+ "blocks.15.attn1.to_q.biases": "1.safetensors",
739
+ "blocks.15.attn1.to_q.bias": "1.safetensors",
740
+ "blocks.15.attn1.to_k.weight": "1.safetensors",
741
+ "blocks.15.attn1.to_k.scales": "1.safetensors",
742
+ "blocks.15.attn1.to_k.biases": "1.safetensors",
743
+ "blocks.15.attn1.to_k.bias": "1.safetensors",
744
+ "blocks.15.attn1.to_v.weight": "1.safetensors",
745
+ "blocks.15.attn1.to_v.scales": "1.safetensors",
746
+ "blocks.15.attn1.to_v.biases": "1.safetensors",
747
+ "blocks.15.attn1.to_v.bias": "1.safetensors",
748
+ "blocks.15.attn1.to_out.0.weight": "1.safetensors",
749
+ "blocks.15.attn1.to_out.0.scales": "1.safetensors",
750
+ "blocks.15.attn1.to_out.0.biases": "1.safetensors",
751
+ "blocks.15.attn1.to_out.0.bias": "1.safetensors",
752
+ "blocks.15.attn1.norm_q.weight": "1.safetensors",
753
+ "blocks.15.attn1.norm_k.weight": "1.safetensors",
754
+ "blocks.15.attn2.to_q.weight": "1.safetensors",
755
+ "blocks.15.attn2.to_q.scales": "1.safetensors",
756
+ "blocks.15.attn2.to_q.biases": "1.safetensors",
757
+ "blocks.15.attn2.to_q.bias": "1.safetensors",
758
+ "blocks.15.attn2.to_k.weight": "1.safetensors",
759
+ "blocks.15.attn2.to_k.scales": "1.safetensors",
760
+ "blocks.15.attn2.to_k.biases": "1.safetensors",
761
+ "blocks.15.attn2.to_k.bias": "1.safetensors",
762
+ "blocks.15.attn2.to_v.weight": "1.safetensors",
763
+ "blocks.15.attn2.to_v.scales": "1.safetensors",
764
+ "blocks.15.attn2.to_v.biases": "1.safetensors",
765
+ "blocks.15.attn2.to_v.bias": "1.safetensors",
766
+ "blocks.15.attn2.to_out.0.weight": "1.safetensors",
767
+ "blocks.15.attn2.to_out.0.scales": "1.safetensors",
768
+ "blocks.15.attn2.to_out.0.biases": "1.safetensors",
769
+ "blocks.15.attn2.to_out.0.bias": "1.safetensors",
770
+ "blocks.15.attn2.norm_q.weight": "1.safetensors",
771
+ "blocks.15.attn2.norm_k.weight": "1.safetensors",
772
+ "blocks.15.norm2.weight": "1.safetensors",
773
+ "blocks.15.norm2.bias": "1.safetensors",
774
+ "blocks.15.ffn.net.0.weight": "1.safetensors",
775
+ "blocks.15.ffn.net.0.scales": "1.safetensors",
776
+ "blocks.15.ffn.net.0.biases": "1.safetensors",
777
+ "blocks.15.ffn.net.0.bias": "1.safetensors",
778
+ "blocks.15.ffn.net.1.weight": "1.safetensors",
779
+ "blocks.15.ffn.net.1.scales": "1.safetensors",
780
+ "blocks.15.ffn.net.1.biases": "1.safetensors",
781
+ "blocks.15.ffn.net.1.bias": "1.safetensors",
782
+ "blocks.15.scale_shift_table": "1.safetensors",
783
+ "blocks.16.attn1.to_q.weight": "1.safetensors",
784
+ "blocks.16.attn1.to_q.scales": "1.safetensors",
785
+ "blocks.16.attn1.to_q.biases": "1.safetensors",
786
+ "blocks.16.attn1.to_q.bias": "1.safetensors",
787
+ "blocks.16.attn1.to_k.weight": "1.safetensors",
788
+ "blocks.16.attn1.to_k.scales": "1.safetensors",
789
+ "blocks.16.attn1.to_k.biases": "1.safetensors",
790
+ "blocks.16.attn1.to_k.bias": "1.safetensors",
791
+ "blocks.16.attn1.to_v.weight": "1.safetensors",
792
+ "blocks.16.attn1.to_v.scales": "1.safetensors",
793
+ "blocks.16.attn1.to_v.biases": "1.safetensors",
794
+ "blocks.16.attn1.to_v.bias": "1.safetensors",
795
+ "blocks.16.attn1.to_out.0.weight": "1.safetensors",
796
+ "blocks.16.attn1.to_out.0.scales": "1.safetensors",
797
+ "blocks.16.attn1.to_out.0.biases": "1.safetensors",
798
+ "blocks.16.attn1.to_out.0.bias": "1.safetensors",
799
+ "blocks.16.attn1.norm_q.weight": "1.safetensors",
800
+ "blocks.16.attn1.norm_k.weight": "1.safetensors",
801
+ "blocks.16.attn2.to_q.weight": "1.safetensors",
802
+ "blocks.16.attn2.to_q.scales": "1.safetensors",
803
+ "blocks.16.attn2.to_q.biases": "1.safetensors",
804
+ "blocks.16.attn2.to_q.bias": "1.safetensors",
805
+ "blocks.16.attn2.to_k.weight": "1.safetensors",
806
+ "blocks.16.attn2.to_k.scales": "1.safetensors",
807
+ "blocks.16.attn2.to_k.biases": "1.safetensors",
808
+ "blocks.16.attn2.to_k.bias": "1.safetensors",
809
+ "blocks.16.attn2.to_v.weight": "1.safetensors",
810
+ "blocks.16.attn2.to_v.scales": "1.safetensors",
811
+ "blocks.16.attn2.to_v.biases": "1.safetensors",
812
+ "blocks.16.attn2.to_v.bias": "1.safetensors",
813
+ "blocks.16.attn2.to_out.0.weight": "1.safetensors",
814
+ "blocks.16.attn2.to_out.0.scales": "1.safetensors",
815
+ "blocks.16.attn2.to_out.0.biases": "1.safetensors",
816
+ "blocks.16.attn2.to_out.0.bias": "1.safetensors",
817
+ "blocks.16.attn2.norm_q.weight": "1.safetensors",
818
+ "blocks.16.attn2.norm_k.weight": "1.safetensors",
819
+ "blocks.16.norm2.weight": "1.safetensors",
820
+ "blocks.16.norm2.bias": "1.safetensors",
821
+ "blocks.16.ffn.net.0.weight": "1.safetensors",
822
+ "blocks.16.ffn.net.0.scales": "1.safetensors",
823
+ "blocks.16.ffn.net.0.biases": "1.safetensors",
824
+ "blocks.16.ffn.net.0.bias": "1.safetensors",
825
+ "blocks.16.ffn.net.1.weight": "1.safetensors",
826
+ "blocks.16.ffn.net.1.scales": "1.safetensors",
827
+ "blocks.16.ffn.net.1.biases": "1.safetensors",
828
+ "blocks.16.ffn.net.1.bias": "1.safetensors",
829
+ "blocks.16.scale_shift_table": "1.safetensors",
830
+ "blocks.17.attn1.to_q.weight": "1.safetensors",
831
+ "blocks.17.attn1.to_q.scales": "1.safetensors",
832
+ "blocks.17.attn1.to_q.biases": "1.safetensors",
833
+ "blocks.17.attn1.to_q.bias": "1.safetensors",
834
+ "blocks.17.attn1.to_k.weight": "1.safetensors",
835
+ "blocks.17.attn1.to_k.scales": "1.safetensors",
836
+ "blocks.17.attn1.to_k.biases": "1.safetensors",
837
+ "blocks.17.attn1.to_k.bias": "1.safetensors",
838
+ "blocks.17.attn1.to_v.weight": "1.safetensors",
839
+ "blocks.17.attn1.to_v.scales": "1.safetensors",
840
+ "blocks.17.attn1.to_v.biases": "1.safetensors",
841
+ "blocks.17.attn1.to_v.bias": "1.safetensors",
842
+ "blocks.17.attn1.to_out.0.weight": "1.safetensors",
843
+ "blocks.17.attn1.to_out.0.scales": "1.safetensors",
844
+ "blocks.17.attn1.to_out.0.biases": "1.safetensors",
845
+ "blocks.17.attn1.to_out.0.bias": "1.safetensors",
846
+ "blocks.17.attn1.norm_q.weight": "1.safetensors",
847
+ "blocks.17.attn1.norm_k.weight": "1.safetensors",
848
+ "blocks.17.attn2.to_q.weight": "1.safetensors",
849
+ "blocks.17.attn2.to_q.scales": "1.safetensors",
850
+ "blocks.17.attn2.to_q.biases": "1.safetensors",
851
+ "blocks.17.attn2.to_q.bias": "1.safetensors",
852
+ "blocks.17.attn2.to_k.weight": "1.safetensors",
853
+ "blocks.17.attn2.to_k.scales": "1.safetensors",
854
+ "blocks.17.attn2.to_k.biases": "1.safetensors",
855
+ "blocks.17.attn2.to_k.bias": "1.safetensors",
856
+ "blocks.17.attn2.to_v.weight": "1.safetensors",
857
+ "blocks.17.attn2.to_v.scales": "1.safetensors",
858
+ "blocks.17.attn2.to_v.biases": "1.safetensors",
859
+ "blocks.17.attn2.to_v.bias": "1.safetensors",
860
+ "blocks.17.attn2.to_out.0.weight": "1.safetensors",
861
+ "blocks.17.attn2.to_out.0.scales": "1.safetensors",
862
+ "blocks.17.attn2.to_out.0.biases": "1.safetensors",
863
+ "blocks.17.attn2.to_out.0.bias": "1.safetensors",
864
+ "blocks.17.attn2.norm_q.weight": "1.safetensors",
865
+ "blocks.17.attn2.norm_k.weight": "1.safetensors",
866
+ "blocks.17.norm2.weight": "1.safetensors",
867
+ "blocks.17.norm2.bias": "1.safetensors",
868
+ "blocks.17.ffn.net.0.weight": "1.safetensors",
869
+ "blocks.17.ffn.net.0.scales": "1.safetensors",
870
+ "blocks.17.ffn.net.0.biases": "1.safetensors",
871
+ "blocks.17.ffn.net.0.bias": "1.safetensors",
872
+ "blocks.17.ffn.net.1.weight": "1.safetensors",
873
+ "blocks.17.ffn.net.1.scales": "1.safetensors",
874
+ "blocks.17.ffn.net.1.biases": "1.safetensors",
875
+ "blocks.17.ffn.net.1.bias": "1.safetensors",
876
+ "blocks.17.scale_shift_table": "1.safetensors",
877
+ "blocks.18.attn1.to_q.weight": "1.safetensors",
878
+ "blocks.18.attn1.to_q.scales": "1.safetensors",
879
+ "blocks.18.attn1.to_q.biases": "1.safetensors",
880
+ "blocks.18.attn1.to_q.bias": "1.safetensors",
881
+ "blocks.18.attn1.to_k.weight": "1.safetensors",
882
+ "blocks.18.attn1.to_k.scales": "1.safetensors",
883
+ "blocks.18.attn1.to_k.biases": "1.safetensors",
884
+ "blocks.18.attn1.to_k.bias": "1.safetensors",
885
+ "blocks.18.attn1.to_v.weight": "1.safetensors",
886
+ "blocks.18.attn1.to_v.scales": "1.safetensors",
887
+ "blocks.18.attn1.to_v.biases": "1.safetensors",
888
+ "blocks.18.attn1.to_v.bias": "1.safetensors",
889
+ "blocks.18.attn1.to_out.0.weight": "1.safetensors",
890
+ "blocks.18.attn1.to_out.0.scales": "1.safetensors",
891
+ "blocks.18.attn1.to_out.0.biases": "1.safetensors",
892
+ "blocks.18.attn1.to_out.0.bias": "1.safetensors",
893
+ "blocks.18.attn1.norm_q.weight": "1.safetensors",
894
+ "blocks.18.attn1.norm_k.weight": "1.safetensors",
895
+ "blocks.18.attn2.to_q.weight": "1.safetensors",
896
+ "blocks.18.attn2.to_q.scales": "1.safetensors",
897
+ "blocks.18.attn2.to_q.biases": "1.safetensors",
898
+ "blocks.18.attn2.to_q.bias": "1.safetensors",
899
+ "blocks.18.attn2.to_k.weight": "1.safetensors",
900
+ "blocks.18.attn2.to_k.scales": "1.safetensors",
901
+ "blocks.18.attn2.to_k.biases": "1.safetensors",
902
+ "blocks.18.attn2.to_k.bias": "1.safetensors",
903
+ "blocks.18.attn2.to_v.weight": "1.safetensors",
904
+ "blocks.18.attn2.to_v.scales": "1.safetensors",
905
+ "blocks.18.attn2.to_v.biases": "1.safetensors",
906
+ "blocks.18.attn2.to_v.bias": "1.safetensors",
907
+ "blocks.18.attn2.to_out.0.weight": "1.safetensors",
908
+ "blocks.18.attn2.to_out.0.scales": "1.safetensors",
909
+ "blocks.18.attn2.to_out.0.biases": "1.safetensors",
910
+ "blocks.18.attn2.to_out.0.bias": "1.safetensors",
911
+ "blocks.18.attn2.norm_q.weight": "1.safetensors",
912
+ "blocks.18.attn2.norm_k.weight": "1.safetensors",
913
+ "blocks.18.norm2.weight": "1.safetensors",
914
+ "blocks.18.norm2.bias": "1.safetensors",
915
+ "blocks.18.ffn.net.0.weight": "1.safetensors",
916
+ "blocks.18.ffn.net.0.scales": "1.safetensors",
917
+ "blocks.18.ffn.net.0.biases": "1.safetensors",
918
+ "blocks.18.ffn.net.0.bias": "1.safetensors",
919
+ "blocks.18.ffn.net.1.weight": "1.safetensors",
920
+ "blocks.18.ffn.net.1.scales": "1.safetensors",
921
+ "blocks.18.ffn.net.1.biases": "1.safetensors",
922
+ "blocks.18.ffn.net.1.bias": "1.safetensors",
923
+ "blocks.18.scale_shift_table": "1.safetensors",
924
+ "blocks.19.attn1.to_q.weight": "1.safetensors",
925
+ "blocks.19.attn1.to_q.scales": "1.safetensors",
926
+ "blocks.19.attn1.to_q.biases": "1.safetensors",
927
+ "blocks.19.attn1.to_q.bias": "1.safetensors",
928
+ "blocks.19.attn1.to_k.weight": "1.safetensors",
929
+ "blocks.19.attn1.to_k.scales": "1.safetensors",
930
+ "blocks.19.attn1.to_k.biases": "1.safetensors",
931
+ "blocks.19.attn1.to_k.bias": "1.safetensors",
932
+ "blocks.19.attn1.to_v.weight": "1.safetensors",
933
+ "blocks.19.attn1.to_v.scales": "1.safetensors",
934
+ "blocks.19.attn1.to_v.biases": "1.safetensors",
935
+ "blocks.19.attn1.to_v.bias": "1.safetensors",
936
+ "blocks.19.attn1.to_out.0.weight": "1.safetensors",
937
+ "blocks.19.attn1.to_out.0.scales": "1.safetensors",
938
+ "blocks.19.attn1.to_out.0.biases": "1.safetensors",
939
+ "blocks.19.attn1.to_out.0.bias": "1.safetensors",
940
+ "blocks.19.attn1.norm_q.weight": "1.safetensors",
941
+ "blocks.19.attn1.norm_k.weight": "1.safetensors",
942
+ "blocks.19.attn2.to_q.weight": "1.safetensors",
943
+ "blocks.19.attn2.to_q.scales": "1.safetensors",
944
+ "blocks.19.attn2.to_q.biases": "1.safetensors",
945
+ "blocks.19.attn2.to_q.bias": "1.safetensors",
946
+ "blocks.19.attn2.to_k.weight": "1.safetensors",
947
+ "blocks.19.attn2.to_k.scales": "1.safetensors",
948
+ "blocks.19.attn2.to_k.biases": "1.safetensors",
949
+ "blocks.19.attn2.to_k.bias": "1.safetensors",
950
+ "blocks.19.attn2.to_v.weight": "1.safetensors",
951
+ "blocks.19.attn2.to_v.scales": "1.safetensors",
952
+ "blocks.19.attn2.to_v.biases": "1.safetensors",
953
+ "blocks.19.attn2.to_v.bias": "1.safetensors",
954
+ "blocks.19.attn2.to_out.0.weight": "1.safetensors",
955
+ "blocks.19.attn2.to_out.0.scales": "1.safetensors",
956
+ "blocks.19.attn2.to_out.0.biases": "1.safetensors",
957
+ "blocks.19.attn2.to_out.0.bias": "1.safetensors",
958
+ "blocks.19.attn2.norm_q.weight": "1.safetensors",
959
+ "blocks.19.attn2.norm_k.weight": "1.safetensors",
960
+ "blocks.19.norm2.weight": "1.safetensors",
961
+ "blocks.19.norm2.bias": "1.safetensors",
962
+ "blocks.19.ffn.net.0.weight": "1.safetensors",
963
+ "blocks.19.ffn.net.0.scales": "1.safetensors",
964
+ "blocks.19.ffn.net.0.biases": "1.safetensors",
965
+ "blocks.19.ffn.net.0.bias": "1.safetensors",
966
+ "blocks.19.ffn.net.1.weight": "1.safetensors",
967
+ "blocks.19.ffn.net.1.scales": "1.safetensors",
968
+ "blocks.19.ffn.net.1.biases": "1.safetensors",
969
+ "blocks.19.ffn.net.1.bias": "1.safetensors",
970
+ "blocks.19.scale_shift_table": "1.safetensors",
971
+ "blocks.20.attn1.to_q.weight": "1.safetensors",
972
+ "blocks.20.attn1.to_q.scales": "1.safetensors",
973
+ "blocks.20.attn1.to_q.biases": "1.safetensors",
974
+ "blocks.20.attn1.to_q.bias": "1.safetensors",
975
+ "blocks.20.attn1.to_k.weight": "1.safetensors",
976
+ "blocks.20.attn1.to_k.scales": "1.safetensors",
977
+ "blocks.20.attn1.to_k.biases": "1.safetensors",
978
+ "blocks.20.attn1.to_k.bias": "1.safetensors",
979
+ "blocks.20.attn1.to_v.weight": "1.safetensors",
980
+ "blocks.20.attn1.to_v.scales": "1.safetensors",
981
+ "blocks.20.attn1.to_v.biases": "1.safetensors",
982
+ "blocks.20.attn1.to_v.bias": "1.safetensors",
983
+ "blocks.20.attn1.to_out.0.weight": "1.safetensors",
984
+ "blocks.20.attn1.to_out.0.scales": "1.safetensors",
985
+ "blocks.20.attn1.to_out.0.biases": "1.safetensors",
986
+ "blocks.20.attn1.to_out.0.bias": "1.safetensors",
987
+ "blocks.20.attn1.norm_q.weight": "1.safetensors",
988
+ "blocks.20.attn1.norm_k.weight": "1.safetensors",
989
+ "blocks.20.attn2.to_q.weight": "1.safetensors",
990
+ "blocks.20.attn2.to_q.scales": "1.safetensors",
991
+ "blocks.20.attn2.to_q.biases": "1.safetensors",
992
+ "blocks.20.attn2.to_q.bias": "1.safetensors",
993
+ "blocks.20.attn2.to_k.weight": "1.safetensors",
994
+ "blocks.20.attn2.to_k.scales": "1.safetensors",
995
+ "blocks.20.attn2.to_k.biases": "1.safetensors",
996
+ "blocks.20.attn2.to_k.bias": "1.safetensors",
997
+ "blocks.20.attn2.to_v.weight": "1.safetensors",
998
+ "blocks.20.attn2.to_v.scales": "1.safetensors",
999
+ "blocks.20.attn2.to_v.biases": "1.safetensors",
1000
+ "blocks.20.attn2.to_v.bias": "1.safetensors",
1001
+ "blocks.20.attn2.to_out.0.weight": "1.safetensors",
1002
+ "blocks.20.attn2.to_out.0.scales": "1.safetensors",
1003
+ "blocks.20.attn2.to_out.0.biases": "1.safetensors",
1004
+ "blocks.20.attn2.to_out.0.bias": "1.safetensors",
1005
+ "blocks.20.attn2.norm_q.weight": "1.safetensors",
1006
+ "blocks.20.attn2.norm_k.weight": "1.safetensors",
1007
+ "blocks.20.norm2.weight": "1.safetensors",
1008
+ "blocks.20.norm2.bias": "1.safetensors",
1009
+ "blocks.20.ffn.net.0.weight": "1.safetensors",
1010
+ "blocks.20.ffn.net.0.scales": "1.safetensors",
1011
+ "blocks.20.ffn.net.0.biases": "1.safetensors",
1012
+ "blocks.20.ffn.net.0.bias": "1.safetensors",
1013
+ "blocks.20.ffn.net.1.weight": "1.safetensors",
1014
+ "blocks.20.ffn.net.1.scales": "1.safetensors",
1015
+ "blocks.20.ffn.net.1.biases": "1.safetensors",
1016
+ "blocks.20.ffn.net.1.bias": "1.safetensors",
1017
+ "blocks.20.scale_shift_table": "1.safetensors",
1018
+ "blocks.21.attn1.to_q.weight": "1.safetensors",
1019
+ "blocks.21.attn1.to_q.scales": "1.safetensors",
1020
+ "blocks.21.attn1.to_q.biases": "1.safetensors",
1021
+ "blocks.21.attn1.to_q.bias": "1.safetensors",
1022
+ "blocks.21.attn1.to_k.weight": "1.safetensors",
1023
+ "blocks.21.attn1.to_k.scales": "1.safetensors",
1024
+ "blocks.21.attn1.to_k.biases": "1.safetensors",
1025
+ "blocks.21.attn1.to_k.bias": "1.safetensors",
1026
+ "blocks.21.attn1.to_v.weight": "1.safetensors",
1027
+ "blocks.21.attn1.to_v.scales": "1.safetensors",
1028
+ "blocks.21.attn1.to_v.biases": "1.safetensors",
1029
+ "blocks.21.attn1.to_v.bias": "1.safetensors",
1030
+ "blocks.21.attn1.to_out.0.weight": "1.safetensors",
1031
+ "blocks.21.attn1.to_out.0.scales": "1.safetensors",
1032
+ "blocks.21.attn1.to_out.0.biases": "1.safetensors",
1033
+ "blocks.21.attn1.to_out.0.bias": "1.safetensors",
1034
+ "blocks.21.attn1.norm_q.weight": "1.safetensors",
1035
+ "blocks.21.attn1.norm_k.weight": "1.safetensors",
1036
+ "blocks.21.attn2.to_q.weight": "1.safetensors",
1037
+ "blocks.21.attn2.to_q.scales": "1.safetensors",
1038
+ "blocks.21.attn2.to_q.biases": "1.safetensors",
1039
+ "blocks.21.attn2.to_q.bias": "1.safetensors",
1040
+ "blocks.21.attn2.to_k.weight": "1.safetensors",
1041
+ "blocks.21.attn2.to_k.scales": "1.safetensors",
1042
+ "blocks.21.attn2.to_k.biases": "1.safetensors",
1043
+ "blocks.21.attn2.to_k.bias": "1.safetensors",
1044
+ "blocks.21.attn2.to_v.weight": "1.safetensors",
1045
+ "blocks.21.attn2.to_v.scales": "1.safetensors",
1046
+ "blocks.21.attn2.to_v.biases": "1.safetensors",
1047
+ "blocks.21.attn2.to_v.bias": "1.safetensors",
1048
+ "blocks.21.attn2.to_out.0.weight": "1.safetensors",
1049
+ "blocks.21.attn2.to_out.0.scales": "1.safetensors",
1050
+ "blocks.21.attn2.to_out.0.biases": "1.safetensors",
1051
+ "blocks.21.attn2.to_out.0.bias": "1.safetensors",
1052
+ "blocks.21.attn2.norm_q.weight": "1.safetensors",
1053
+ "blocks.21.attn2.norm_k.weight": "1.safetensors",
1054
+ "blocks.21.norm2.weight": "1.safetensors",
1055
+ "blocks.21.norm2.bias": "1.safetensors",
1056
+ "blocks.21.ffn.net.0.weight": "1.safetensors",
1057
+ "blocks.21.ffn.net.0.scales": "1.safetensors",
1058
+ "blocks.21.ffn.net.0.biases": "1.safetensors",
1059
+ "blocks.21.ffn.net.0.bias": "1.safetensors",
1060
+ "blocks.21.ffn.net.1.weight": "1.safetensors",
1061
+ "blocks.21.ffn.net.1.scales": "1.safetensors",
1062
+ "blocks.21.ffn.net.1.biases": "1.safetensors",
1063
+ "blocks.21.ffn.net.1.bias": "1.safetensors",
1064
+ "blocks.21.scale_shift_table": "1.safetensors",
1065
+ "blocks.22.attn1.to_q.weight": "1.safetensors",
1066
+ "blocks.22.attn1.to_q.scales": "1.safetensors",
1067
+ "blocks.22.attn1.to_q.biases": "1.safetensors",
1068
+ "blocks.22.attn1.to_q.bias": "1.safetensors",
1069
+ "blocks.22.attn1.to_k.weight": "1.safetensors",
1070
+ "blocks.22.attn1.to_k.scales": "1.safetensors",
1071
+ "blocks.22.attn1.to_k.biases": "1.safetensors",
1072
+ "blocks.22.attn1.to_k.bias": "1.safetensors",
1073
+ "blocks.22.attn1.to_v.weight": "1.safetensors",
1074
+ "blocks.22.attn1.to_v.scales": "1.safetensors",
1075
+ "blocks.22.attn1.to_v.biases": "1.safetensors",
1076
+ "blocks.22.attn1.to_v.bias": "1.safetensors",
1077
+ "blocks.22.attn1.to_out.0.weight": "1.safetensors",
1078
+ "blocks.22.attn1.to_out.0.scales": "1.safetensors",
1079
+ "blocks.22.attn1.to_out.0.biases": "1.safetensors",
1080
+ "blocks.22.attn1.to_out.0.bias": "1.safetensors",
1081
+ "blocks.22.attn1.norm_q.weight": "1.safetensors",
1082
+ "blocks.22.attn1.norm_k.weight": "1.safetensors",
1083
+ "blocks.22.attn2.to_q.weight": "1.safetensors",
1084
+ "blocks.22.attn2.to_q.scales": "1.safetensors",
1085
+ "blocks.22.attn2.to_q.biases": "1.safetensors",
1086
+ "blocks.22.attn2.to_q.bias": "1.safetensors",
1087
+ "blocks.22.attn2.to_k.weight": "1.safetensors",
1088
+ "blocks.22.attn2.to_k.scales": "1.safetensors",
1089
+ "blocks.22.attn2.to_k.biases": "1.safetensors",
1090
+ "blocks.22.attn2.to_k.bias": "1.safetensors",
1091
+ "blocks.22.attn2.to_v.weight": "1.safetensors",
1092
+ "blocks.22.attn2.to_v.scales": "1.safetensors",
1093
+ "blocks.22.attn2.to_v.biases": "1.safetensors",
1094
+ "blocks.22.attn2.to_v.bias": "1.safetensors",
1095
+ "blocks.22.attn2.to_out.0.weight": "1.safetensors",
1096
+ "blocks.22.attn2.to_out.0.scales": "1.safetensors",
1097
+ "blocks.22.attn2.to_out.0.biases": "1.safetensors",
1098
+ "blocks.22.attn2.to_out.0.bias": "1.safetensors",
1099
+ "blocks.22.attn2.norm_q.weight": "1.safetensors",
1100
+ "blocks.22.attn2.norm_k.weight": "1.safetensors",
1101
+ "blocks.22.norm2.weight": "1.safetensors",
1102
+ "blocks.22.norm2.bias": "1.safetensors",
1103
+ "blocks.22.ffn.net.0.weight": "1.safetensors",
1104
+ "blocks.22.ffn.net.0.scales": "1.safetensors",
1105
+ "blocks.22.ffn.net.0.biases": "1.safetensors",
1106
+ "blocks.22.ffn.net.0.bias": "1.safetensors",
1107
+ "blocks.22.ffn.net.1.weight": "1.safetensors",
1108
+ "blocks.22.ffn.net.1.scales": "1.safetensors",
1109
+ "blocks.22.ffn.net.1.biases": "1.safetensors",
1110
+ "blocks.22.ffn.net.1.bias": "1.safetensors",
1111
+ "blocks.22.scale_shift_table": "1.safetensors",
1112
+ "blocks.23.attn1.to_q.weight": "1.safetensors",
1113
+ "blocks.23.attn1.to_q.scales": "1.safetensors",
1114
+ "blocks.23.attn1.to_q.biases": "1.safetensors",
1115
+ "blocks.23.attn1.to_q.bias": "1.safetensors",
1116
+ "blocks.23.attn1.to_k.weight": "1.safetensors",
1117
+ "blocks.23.attn1.to_k.scales": "1.safetensors",
1118
+ "blocks.23.attn1.to_k.biases": "1.safetensors",
1119
+ "blocks.23.attn1.to_k.bias": "1.safetensors",
1120
+ "blocks.23.attn1.to_v.weight": "1.safetensors",
1121
+ "blocks.23.attn1.to_v.scales": "1.safetensors",
1122
+ "blocks.23.attn1.to_v.biases": "1.safetensors",
1123
+ "blocks.23.attn1.to_v.bias": "1.safetensors",
1124
+ "blocks.23.attn1.to_out.0.weight": "1.safetensors",
1125
+ "blocks.23.attn1.to_out.0.scales": "1.safetensors",
1126
+ "blocks.23.attn1.to_out.0.biases": "1.safetensors",
1127
+ "blocks.23.attn1.to_out.0.bias": "1.safetensors",
1128
+ "blocks.23.attn1.norm_q.weight": "1.safetensors",
1129
+ "blocks.23.attn1.norm_k.weight": "1.safetensors",
1130
+ "blocks.23.attn2.to_q.weight": "1.safetensors",
1131
+ "blocks.23.attn2.to_q.scales": "1.safetensors",
1132
+ "blocks.23.attn2.to_q.biases": "1.safetensors",
1133
+ "blocks.23.attn2.to_q.bias": "1.safetensors",
1134
+ "blocks.23.attn2.to_k.weight": "1.safetensors",
1135
+ "blocks.23.attn2.to_k.scales": "1.safetensors",
1136
+ "blocks.23.attn2.to_k.biases": "1.safetensors",
1137
+ "blocks.23.attn2.to_k.bias": "1.safetensors",
1138
+ "blocks.23.attn2.to_v.weight": "1.safetensors",
1139
+ "blocks.23.attn2.to_v.scales": "1.safetensors",
1140
+ "blocks.23.attn2.to_v.biases": "1.safetensors",
1141
+ "blocks.23.attn2.to_v.bias": "1.safetensors",
1142
+ "blocks.23.attn2.to_out.0.weight": "1.safetensors",
1143
+ "blocks.23.attn2.to_out.0.scales": "1.safetensors",
1144
+ "blocks.23.attn2.to_out.0.biases": "1.safetensors",
1145
+ "blocks.23.attn2.to_out.0.bias": "1.safetensors",
1146
+ "blocks.23.attn2.norm_q.weight": "1.safetensors",
1147
+ "blocks.23.attn2.norm_k.weight": "1.safetensors",
1148
+ "blocks.23.norm2.weight": "1.safetensors",
1149
+ "blocks.23.norm2.bias": "1.safetensors",
1150
+ "blocks.23.ffn.net.0.weight": "1.safetensors",
1151
+ "blocks.23.ffn.net.0.scales": "1.safetensors",
1152
+ "blocks.23.ffn.net.0.biases": "1.safetensors",
1153
+ "blocks.23.ffn.net.0.bias": "1.safetensors",
1154
+ "blocks.23.ffn.net.1.weight": "1.safetensors",
1155
+ "blocks.23.ffn.net.1.scales": "1.safetensors",
1156
+ "blocks.23.ffn.net.1.biases": "1.safetensors",
1157
+ "blocks.23.ffn.net.1.bias": "1.safetensors",
1158
+ "blocks.23.scale_shift_table": "1.safetensors",
1159
+ "blocks.24.attn1.to_q.weight": "1.safetensors",
1160
+ "blocks.24.attn1.to_q.scales": "1.safetensors",
1161
+ "blocks.24.attn1.to_q.biases": "1.safetensors",
1162
+ "blocks.24.attn1.to_q.bias": "1.safetensors",
1163
+ "blocks.24.attn1.to_k.weight": "2.safetensors",
1164
+ "blocks.24.attn1.to_k.scales": "2.safetensors",
1165
+ "blocks.24.attn1.to_k.biases": "2.safetensors",
1166
+ "blocks.24.attn1.to_k.bias": "2.safetensors",
1167
+ "blocks.24.attn1.to_v.weight": "2.safetensors",
1168
+ "blocks.24.attn1.to_v.scales": "2.safetensors",
1169
+ "blocks.24.attn1.to_v.biases": "2.safetensors",
1170
+ "blocks.24.attn1.to_v.bias": "2.safetensors",
1171
+ "blocks.24.attn1.to_out.0.weight": "2.safetensors",
1172
+ "blocks.24.attn1.to_out.0.scales": "2.safetensors",
1173
+ "blocks.24.attn1.to_out.0.biases": "2.safetensors",
1174
+ "blocks.24.attn1.to_out.0.bias": "2.safetensors",
1175
+ "blocks.24.attn1.norm_q.weight": "2.safetensors",
1176
+ "blocks.24.attn1.norm_k.weight": "2.safetensors",
1177
+ "blocks.24.attn2.to_q.weight": "2.safetensors",
1178
+ "blocks.24.attn2.to_q.scales": "2.safetensors",
1179
+ "blocks.24.attn2.to_q.biases": "2.safetensors",
1180
+ "blocks.24.attn2.to_q.bias": "2.safetensors",
1181
+ "blocks.24.attn2.to_k.weight": "2.safetensors",
1182
+ "blocks.24.attn2.to_k.scales": "2.safetensors",
1183
+ "blocks.24.attn2.to_k.biases": "2.safetensors",
1184
+ "blocks.24.attn2.to_k.bias": "2.safetensors",
1185
+ "blocks.24.attn2.to_v.weight": "2.safetensors",
1186
+ "blocks.24.attn2.to_v.scales": "2.safetensors",
1187
+ "blocks.24.attn2.to_v.biases": "2.safetensors",
1188
+ "blocks.24.attn2.to_v.bias": "2.safetensors",
1189
+ "blocks.24.attn2.to_out.0.weight": "2.safetensors",
1190
+ "blocks.24.attn2.to_out.0.scales": "2.safetensors",
1191
+ "blocks.24.attn2.to_out.0.biases": "2.safetensors",
1192
+ "blocks.24.attn2.to_out.0.bias": "2.safetensors",
1193
+ "blocks.24.attn2.norm_q.weight": "2.safetensors",
1194
+ "blocks.24.attn2.norm_k.weight": "2.safetensors",
1195
+ "blocks.24.norm2.weight": "2.safetensors",
1196
+ "blocks.24.norm2.bias": "2.safetensors",
1197
+ "blocks.24.ffn.net.0.weight": "2.safetensors",
1198
+ "blocks.24.ffn.net.0.scales": "2.safetensors",
1199
+ "blocks.24.ffn.net.0.biases": "2.safetensors",
1200
+ "blocks.24.ffn.net.0.bias": "2.safetensors",
1201
+ "blocks.24.ffn.net.1.weight": "2.safetensors",
1202
+ "blocks.24.ffn.net.1.scales": "2.safetensors",
1203
+ "blocks.24.ffn.net.1.biases": "2.safetensors",
1204
+ "blocks.24.ffn.net.1.bias": "2.safetensors",
1205
+ "blocks.24.scale_shift_table": "2.safetensors",
1206
+ "blocks.25.attn1.to_q.weight": "2.safetensors",
1207
+ "blocks.25.attn1.to_q.scales": "2.safetensors",
1208
+ "blocks.25.attn1.to_q.biases": "2.safetensors",
1209
+ "blocks.25.attn1.to_q.bias": "2.safetensors",
1210
+ "blocks.25.attn1.to_k.weight": "2.safetensors",
1211
+ "blocks.25.attn1.to_k.scales": "2.safetensors",
1212
+ "blocks.25.attn1.to_k.biases": "2.safetensors",
1213
+ "blocks.25.attn1.to_k.bias": "2.safetensors",
1214
+ "blocks.25.attn1.to_v.weight": "2.safetensors",
1215
+ "blocks.25.attn1.to_v.scales": "2.safetensors",
1216
+ "blocks.25.attn1.to_v.biases": "2.safetensors",
1217
+ "blocks.25.attn1.to_v.bias": "2.safetensors",
1218
+ "blocks.25.attn1.to_out.0.weight": "2.safetensors",
1219
+ "blocks.25.attn1.to_out.0.scales": "2.safetensors",
1220
+ "blocks.25.attn1.to_out.0.biases": "2.safetensors",
1221
+ "blocks.25.attn1.to_out.0.bias": "2.safetensors",
1222
+ "blocks.25.attn1.norm_q.weight": "2.safetensors",
1223
+ "blocks.25.attn1.norm_k.weight": "2.safetensors",
1224
+ "blocks.25.attn2.to_q.weight": "2.safetensors",
1225
+ "blocks.25.attn2.to_q.scales": "2.safetensors",
1226
+ "blocks.25.attn2.to_q.biases": "2.safetensors",
1227
+ "blocks.25.attn2.to_q.bias": "2.safetensors",
1228
+ "blocks.25.attn2.to_k.weight": "2.safetensors",
1229
+ "blocks.25.attn2.to_k.scales": "2.safetensors",
1230
+ "blocks.25.attn2.to_k.biases": "2.safetensors",
1231
+ "blocks.25.attn2.to_k.bias": "2.safetensors",
1232
+ "blocks.25.attn2.to_v.weight": "2.safetensors",
1233
+ "blocks.25.attn2.to_v.scales": "2.safetensors",
1234
+ "blocks.25.attn2.to_v.biases": "2.safetensors",
1235
+ "blocks.25.attn2.to_v.bias": "2.safetensors",
1236
+ "blocks.25.attn2.to_out.0.weight": "2.safetensors",
1237
+ "blocks.25.attn2.to_out.0.scales": "2.safetensors",
1238
+ "blocks.25.attn2.to_out.0.biases": "2.safetensors",
1239
+ "blocks.25.attn2.to_out.0.bias": "2.safetensors",
1240
+ "blocks.25.attn2.norm_q.weight": "2.safetensors",
1241
+ "blocks.25.attn2.norm_k.weight": "2.safetensors",
1242
+ "blocks.25.norm2.weight": "2.safetensors",
1243
+ "blocks.25.norm2.bias": "2.safetensors",
1244
+ "blocks.25.ffn.net.0.weight": "2.safetensors",
1245
+ "blocks.25.ffn.net.0.scales": "2.safetensors",
1246
+ "blocks.25.ffn.net.0.biases": "2.safetensors",
1247
+ "blocks.25.ffn.net.0.bias": "2.safetensors",
1248
+ "blocks.25.ffn.net.1.weight": "2.safetensors",
1249
+ "blocks.25.ffn.net.1.scales": "2.safetensors",
1250
+ "blocks.25.ffn.net.1.biases": "2.safetensors",
1251
+ "blocks.25.ffn.net.1.bias": "2.safetensors",
1252
+ "blocks.25.scale_shift_table": "2.safetensors",
1253
+ "blocks.26.attn1.to_q.weight": "2.safetensors",
1254
+ "blocks.26.attn1.to_q.scales": "2.safetensors",
1255
+ "blocks.26.attn1.to_q.biases": "2.safetensors",
1256
+ "blocks.26.attn1.to_q.bias": "2.safetensors",
1257
+ "blocks.26.attn1.to_k.weight": "2.safetensors",
1258
+ "blocks.26.attn1.to_k.scales": "2.safetensors",
1259
+ "blocks.26.attn1.to_k.biases": "2.safetensors",
1260
+ "blocks.26.attn1.to_k.bias": "2.safetensors",
1261
+ "blocks.26.attn1.to_v.weight": "2.safetensors",
1262
+ "blocks.26.attn1.to_v.scales": "2.safetensors",
1263
+ "blocks.26.attn1.to_v.biases": "2.safetensors",
1264
+ "blocks.26.attn1.to_v.bias": "2.safetensors",
1265
+ "blocks.26.attn1.to_out.0.weight": "2.safetensors",
1266
+ "blocks.26.attn1.to_out.0.scales": "2.safetensors",
1267
+ "blocks.26.attn1.to_out.0.biases": "2.safetensors",
1268
+ "blocks.26.attn1.to_out.0.bias": "2.safetensors",
1269
+ "blocks.26.attn1.norm_q.weight": "2.safetensors",
1270
+ "blocks.26.attn1.norm_k.weight": "2.safetensors",
1271
+ "blocks.26.attn2.to_q.weight": "2.safetensors",
1272
+ "blocks.26.attn2.to_q.scales": "2.safetensors",
1273
+ "blocks.26.attn2.to_q.biases": "2.safetensors",
1274
+ "blocks.26.attn2.to_q.bias": "2.safetensors",
1275
+ "blocks.26.attn2.to_k.weight": "2.safetensors",
1276
+ "blocks.26.attn2.to_k.scales": "2.safetensors",
1277
+ "blocks.26.attn2.to_k.biases": "2.safetensors",
1278
+ "blocks.26.attn2.to_k.bias": "2.safetensors",
1279
+ "blocks.26.attn2.to_v.weight": "2.safetensors",
1280
+ "blocks.26.attn2.to_v.scales": "2.safetensors",
1281
+ "blocks.26.attn2.to_v.biases": "2.safetensors",
1282
+ "blocks.26.attn2.to_v.bias": "2.safetensors",
1283
+ "blocks.26.attn2.to_out.0.weight": "2.safetensors",
1284
+ "blocks.26.attn2.to_out.0.scales": "2.safetensors",
1285
+ "blocks.26.attn2.to_out.0.biases": "2.safetensors",
1286
+ "blocks.26.attn2.to_out.0.bias": "2.safetensors",
1287
+ "blocks.26.attn2.norm_q.weight": "2.safetensors",
1288
+ "blocks.26.attn2.norm_k.weight": "2.safetensors",
1289
+ "blocks.26.norm2.weight": "2.safetensors",
1290
+ "blocks.26.norm2.bias": "2.safetensors",
1291
+ "blocks.26.ffn.net.0.weight": "2.safetensors",
1292
+ "blocks.26.ffn.net.0.scales": "2.safetensors",
1293
+ "blocks.26.ffn.net.0.biases": "2.safetensors",
1294
+ "blocks.26.ffn.net.0.bias": "2.safetensors",
1295
+ "blocks.26.ffn.net.1.weight": "2.safetensors",
1296
+ "blocks.26.ffn.net.1.scales": "2.safetensors",
1297
+ "blocks.26.ffn.net.1.biases": "2.safetensors",
1298
+ "blocks.26.ffn.net.1.bias": "2.safetensors",
1299
+ "blocks.26.scale_shift_table": "2.safetensors",
1300
+ "blocks.27.attn1.to_q.weight": "2.safetensors",
1301
+ "blocks.27.attn1.to_q.scales": "2.safetensors",
1302
+ "blocks.27.attn1.to_q.biases": "2.safetensors",
1303
+ "blocks.27.attn1.to_q.bias": "2.safetensors",
1304
+ "blocks.27.attn1.to_k.weight": "2.safetensors",
1305
+ "blocks.27.attn1.to_k.scales": "2.safetensors",
1306
+ "blocks.27.attn1.to_k.biases": "2.safetensors",
1307
+ "blocks.27.attn1.to_k.bias": "2.safetensors",
1308
+ "blocks.27.attn1.to_v.weight": "2.safetensors",
1309
+ "blocks.27.attn1.to_v.scales": "2.safetensors",
1310
+ "blocks.27.attn1.to_v.biases": "2.safetensors",
1311
+ "blocks.27.attn1.to_v.bias": "2.safetensors",
1312
+ "blocks.27.attn1.to_out.0.weight": "2.safetensors",
1313
+ "blocks.27.attn1.to_out.0.scales": "2.safetensors",
1314
+ "blocks.27.attn1.to_out.0.biases": "2.safetensors",
1315
+ "blocks.27.attn1.to_out.0.bias": "2.safetensors",
1316
+ "blocks.27.attn1.norm_q.weight": "2.safetensors",
1317
+ "blocks.27.attn1.norm_k.weight": "2.safetensors",
1318
+ "blocks.27.attn2.to_q.weight": "2.safetensors",
1319
+ "blocks.27.attn2.to_q.scales": "2.safetensors",
1320
+ "blocks.27.attn2.to_q.biases": "2.safetensors",
1321
+ "blocks.27.attn2.to_q.bias": "2.safetensors",
1322
+ "blocks.27.attn2.to_k.weight": "2.safetensors",
1323
+ "blocks.27.attn2.to_k.scales": "2.safetensors",
1324
+ "blocks.27.attn2.to_k.biases": "2.safetensors",
1325
+ "blocks.27.attn2.to_k.bias": "2.safetensors",
1326
+ "blocks.27.attn2.to_v.weight": "2.safetensors",
1327
+ "blocks.27.attn2.to_v.scales": "2.safetensors",
1328
+ "blocks.27.attn2.to_v.biases": "2.safetensors",
1329
+ "blocks.27.attn2.to_v.bias": "2.safetensors",
1330
+ "blocks.27.attn2.to_out.0.weight": "2.safetensors",
1331
+ "blocks.27.attn2.to_out.0.scales": "2.safetensors",
1332
+ "blocks.27.attn2.to_out.0.biases": "2.safetensors",
1333
+ "blocks.27.attn2.to_out.0.bias": "2.safetensors",
1334
+ "blocks.27.attn2.norm_q.weight": "2.safetensors",
1335
+ "blocks.27.attn2.norm_k.weight": "2.safetensors",
1336
+ "blocks.27.norm2.weight": "2.safetensors",
1337
+ "blocks.27.norm2.bias": "2.safetensors",
1338
+ "blocks.27.ffn.net.0.weight": "2.safetensors",
1339
+ "blocks.27.ffn.net.0.scales": "2.safetensors",
1340
+ "blocks.27.ffn.net.0.biases": "2.safetensors",
1341
+ "blocks.27.ffn.net.0.bias": "2.safetensors",
1342
+ "blocks.27.ffn.net.1.weight": "2.safetensors",
1343
+ "blocks.27.ffn.net.1.scales": "2.safetensors",
1344
+ "blocks.27.ffn.net.1.biases": "2.safetensors",
1345
+ "blocks.27.ffn.net.1.bias": "2.safetensors",
1346
+ "blocks.27.scale_shift_table": "2.safetensors",
1347
+ "blocks.28.attn1.to_q.weight": "2.safetensors",
1348
+ "blocks.28.attn1.to_q.scales": "2.safetensors",
1349
+ "blocks.28.attn1.to_q.biases": "2.safetensors",
1350
+ "blocks.28.attn1.to_q.bias": "2.safetensors",
1351
+ "blocks.28.attn1.to_k.weight": "2.safetensors",
1352
+ "blocks.28.attn1.to_k.scales": "2.safetensors",
1353
+ "blocks.28.attn1.to_k.biases": "2.safetensors",
1354
+ "blocks.28.attn1.to_k.bias": "2.safetensors",
1355
+ "blocks.28.attn1.to_v.weight": "2.safetensors",
1356
+ "blocks.28.attn1.to_v.scales": "2.safetensors",
1357
+ "blocks.28.attn1.to_v.biases": "2.safetensors",
1358
+ "blocks.28.attn1.to_v.bias": "2.safetensors",
1359
+ "blocks.28.attn1.to_out.0.weight": "2.safetensors",
1360
+ "blocks.28.attn1.to_out.0.scales": "2.safetensors",
1361
+ "blocks.28.attn1.to_out.0.biases": "2.safetensors",
1362
+ "blocks.28.attn1.to_out.0.bias": "2.safetensors",
1363
+ "blocks.28.attn1.norm_q.weight": "2.safetensors",
1364
+ "blocks.28.attn1.norm_k.weight": "2.safetensors",
1365
+ "blocks.28.attn2.to_q.weight": "2.safetensors",
1366
+ "blocks.28.attn2.to_q.scales": "2.safetensors",
1367
+ "blocks.28.attn2.to_q.biases": "2.safetensors",
1368
+ "blocks.28.attn2.to_q.bias": "2.safetensors",
1369
+ "blocks.28.attn2.to_k.weight": "2.safetensors",
1370
+ "blocks.28.attn2.to_k.scales": "2.safetensors",
1371
+ "blocks.28.attn2.to_k.biases": "2.safetensors",
1372
+ "blocks.28.attn2.to_k.bias": "2.safetensors",
1373
+ "blocks.28.attn2.to_v.weight": "2.safetensors",
1374
+ "blocks.28.attn2.to_v.scales": "2.safetensors",
1375
+ "blocks.28.attn2.to_v.biases": "2.safetensors",
1376
+ "blocks.28.attn2.to_v.bias": "2.safetensors",
1377
+ "blocks.28.attn2.to_out.0.weight": "2.safetensors",
1378
+ "blocks.28.attn2.to_out.0.scales": "2.safetensors",
1379
+ "blocks.28.attn2.to_out.0.biases": "2.safetensors",
1380
+ "blocks.28.attn2.to_out.0.bias": "2.safetensors",
1381
+ "blocks.28.attn2.norm_q.weight": "2.safetensors",
1382
+ "blocks.28.attn2.norm_k.weight": "2.safetensors",
1383
+ "blocks.28.norm2.weight": "2.safetensors",
1384
+ "blocks.28.norm2.bias": "2.safetensors",
1385
+ "blocks.28.ffn.net.0.weight": "2.safetensors",
1386
+ "blocks.28.ffn.net.0.scales": "2.safetensors",
1387
+ "blocks.28.ffn.net.0.biases": "2.safetensors",
1388
+ "blocks.28.ffn.net.0.bias": "2.safetensors",
1389
+ "blocks.28.ffn.net.1.weight": "2.safetensors",
1390
+ "blocks.28.ffn.net.1.scales": "2.safetensors",
1391
+ "blocks.28.ffn.net.1.biases": "2.safetensors",
1392
+ "blocks.28.ffn.net.1.bias": "2.safetensors",
1393
+ "blocks.28.scale_shift_table": "2.safetensors",
1394
+ "blocks.29.attn1.to_q.weight": "2.safetensors",
1395
+ "blocks.29.attn1.to_q.scales": "2.safetensors",
1396
+ "blocks.29.attn1.to_q.biases": "2.safetensors",
1397
+ "blocks.29.attn1.to_q.bias": "2.safetensors",
1398
+ "blocks.29.attn1.to_k.weight": "2.safetensors",
1399
+ "blocks.29.attn1.to_k.scales": "2.safetensors",
1400
+ "blocks.29.attn1.to_k.biases": "2.safetensors",
1401
+ "blocks.29.attn1.to_k.bias": "2.safetensors",
1402
+ "blocks.29.attn1.to_v.weight": "2.safetensors",
1403
+ "blocks.29.attn1.to_v.scales": "2.safetensors",
1404
+ "blocks.29.attn1.to_v.biases": "2.safetensors",
1405
+ "blocks.29.attn1.to_v.bias": "2.safetensors",
1406
+ "blocks.29.attn1.to_out.0.weight": "2.safetensors",
1407
+ "blocks.29.attn1.to_out.0.scales": "2.safetensors",
1408
+ "blocks.29.attn1.to_out.0.biases": "2.safetensors",
1409
+ "blocks.29.attn1.to_out.0.bias": "2.safetensors",
1410
+ "blocks.29.attn1.norm_q.weight": "2.safetensors",
1411
+ "blocks.29.attn1.norm_k.weight": "2.safetensors",
1412
+ "blocks.29.attn2.to_q.weight": "2.safetensors",
1413
+ "blocks.29.attn2.to_q.scales": "2.safetensors",
1414
+ "blocks.29.attn2.to_q.biases": "2.safetensors",
1415
+ "blocks.29.attn2.to_q.bias": "2.safetensors",
1416
+ "blocks.29.attn2.to_k.weight": "2.safetensors",
1417
+ "blocks.29.attn2.to_k.scales": "2.safetensors",
1418
+ "blocks.29.attn2.to_k.biases": "2.safetensors",
1419
+ "blocks.29.attn2.to_k.bias": "2.safetensors",
1420
+ "blocks.29.attn2.to_v.weight": "2.safetensors",
1421
+ "blocks.29.attn2.to_v.scales": "2.safetensors",
1422
+ "blocks.29.attn2.to_v.biases": "2.safetensors",
1423
+ "blocks.29.attn2.to_v.bias": "2.safetensors",
1424
+ "blocks.29.attn2.to_out.0.weight": "2.safetensors",
1425
+ "blocks.29.attn2.to_out.0.scales": "2.safetensors",
1426
+ "blocks.29.attn2.to_out.0.biases": "2.safetensors",
1427
+ "blocks.29.attn2.to_out.0.bias": "2.safetensors",
1428
+ "blocks.29.attn2.norm_q.weight": "2.safetensors",
1429
+ "blocks.29.attn2.norm_k.weight": "2.safetensors",
1430
+ "blocks.29.norm2.weight": "2.safetensors",
1431
+ "blocks.29.norm2.bias": "2.safetensors",
1432
+ "blocks.29.ffn.net.0.weight": "2.safetensors",
1433
+ "blocks.29.ffn.net.0.scales": "2.safetensors",
1434
+ "blocks.29.ffn.net.0.biases": "2.safetensors",
1435
+ "blocks.29.ffn.net.0.bias": "2.safetensors",
1436
+ "blocks.29.ffn.net.1.weight": "2.safetensors",
1437
+ "blocks.29.ffn.net.1.scales": "2.safetensors",
1438
+ "blocks.29.ffn.net.1.biases": "2.safetensors",
1439
+ "blocks.29.ffn.net.1.bias": "2.safetensors",
1440
+ "blocks.29.scale_shift_table": "2.safetensors",
1441
+ "proj_out.weight": "2.safetensors",
1442
+ "proj_out.scales": "2.safetensors",
1443
+ "proj_out.biases": "2.safetensors",
1444
+ "proj_out.bias": "2.safetensors",
1445
+ "scale_shift_table": "2.safetensors"
1446
+ }
1447
+ }
vae/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5de7cc01b4737345a64908c281a46b95a1b5a97ef0942f60df6ff1c7e851beb
3
+ size 1409401417
vae/model.safetensors.index.json ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "8",
4
+ "mflux_version": "0.18.6"
5
+ },
6
+ "weight_map": {
7
+ "encoder.conv_in.conv3d.weight": "0.safetensors",
8
+ "encoder.conv_in.conv3d.bias": "0.safetensors",
9
+ "encoder.down_blocks.0.resnets.0.norm1.weight": "0.safetensors",
10
+ "encoder.down_blocks.0.resnets.0.conv1.conv3d.weight": "0.safetensors",
11
+ "encoder.down_blocks.0.resnets.0.conv1.conv3d.bias": "0.safetensors",
12
+ "encoder.down_blocks.0.resnets.0.norm2.weight": "0.safetensors",
13
+ "encoder.down_blocks.0.resnets.0.conv2.conv3d.weight": "0.safetensors",
14
+ "encoder.down_blocks.0.resnets.0.conv2.conv3d.bias": "0.safetensors",
15
+ "encoder.down_blocks.0.resnets.1.norm1.weight": "0.safetensors",
16
+ "encoder.down_blocks.0.resnets.1.conv1.conv3d.weight": "0.safetensors",
17
+ "encoder.down_blocks.0.resnets.1.conv1.conv3d.bias": "0.safetensors",
18
+ "encoder.down_blocks.0.resnets.1.norm2.weight": "0.safetensors",
19
+ "encoder.down_blocks.0.resnets.1.conv2.conv3d.weight": "0.safetensors",
20
+ "encoder.down_blocks.0.resnets.1.conv2.conv3d.bias": "0.safetensors",
21
+ "encoder.down_blocks.0.downsampler.resample_conv.weight": "0.safetensors",
22
+ "encoder.down_blocks.0.downsampler.resample_conv.bias": "0.safetensors",
23
+ "encoder.down_blocks.1.resnets.0.norm1.weight": "0.safetensors",
24
+ "encoder.down_blocks.1.resnets.0.conv1.conv3d.weight": "0.safetensors",
25
+ "encoder.down_blocks.1.resnets.0.conv1.conv3d.bias": "0.safetensors",
26
+ "encoder.down_blocks.1.resnets.0.norm2.weight": "0.safetensors",
27
+ "encoder.down_blocks.1.resnets.0.conv2.conv3d.weight": "0.safetensors",
28
+ "encoder.down_blocks.1.resnets.0.conv2.conv3d.bias": "0.safetensors",
29
+ "encoder.down_blocks.1.resnets.0.conv_shortcut.conv3d.weight": "0.safetensors",
30
+ "encoder.down_blocks.1.resnets.0.conv_shortcut.conv3d.bias": "0.safetensors",
31
+ "encoder.down_blocks.1.resnets.1.norm1.weight": "0.safetensors",
32
+ "encoder.down_blocks.1.resnets.1.conv1.conv3d.weight": "0.safetensors",
33
+ "encoder.down_blocks.1.resnets.1.conv1.conv3d.bias": "0.safetensors",
34
+ "encoder.down_blocks.1.resnets.1.norm2.weight": "0.safetensors",
35
+ "encoder.down_blocks.1.resnets.1.conv2.conv3d.weight": "0.safetensors",
36
+ "encoder.down_blocks.1.resnets.1.conv2.conv3d.bias": "0.safetensors",
37
+ "encoder.down_blocks.1.downsampler.resample_conv.weight": "0.safetensors",
38
+ "encoder.down_blocks.1.downsampler.resample_conv.bias": "0.safetensors",
39
+ "encoder.down_blocks.1.downsampler.time_conv.conv3d.weight": "0.safetensors",
40
+ "encoder.down_blocks.1.downsampler.time_conv.conv3d.bias": "0.safetensors",
41
+ "encoder.down_blocks.2.resnets.0.norm1.weight": "0.safetensors",
42
+ "encoder.down_blocks.2.resnets.0.conv1.conv3d.weight": "0.safetensors",
43
+ "encoder.down_blocks.2.resnets.0.conv1.conv3d.bias": "0.safetensors",
44
+ "encoder.down_blocks.2.resnets.0.norm2.weight": "0.safetensors",
45
+ "encoder.down_blocks.2.resnets.0.conv2.conv3d.weight": "0.safetensors",
46
+ "encoder.down_blocks.2.resnets.0.conv2.conv3d.bias": "0.safetensors",
47
+ "encoder.down_blocks.2.resnets.0.conv_shortcut.conv3d.weight": "0.safetensors",
48
+ "encoder.down_blocks.2.resnets.0.conv_shortcut.conv3d.bias": "0.safetensors",
49
+ "encoder.down_blocks.2.resnets.1.norm1.weight": "0.safetensors",
50
+ "encoder.down_blocks.2.resnets.1.conv1.conv3d.weight": "0.safetensors",
51
+ "encoder.down_blocks.2.resnets.1.conv1.conv3d.bias": "0.safetensors",
52
+ "encoder.down_blocks.2.resnets.1.norm2.weight": "0.safetensors",
53
+ "encoder.down_blocks.2.resnets.1.conv2.conv3d.weight": "0.safetensors",
54
+ "encoder.down_blocks.2.resnets.1.conv2.conv3d.bias": "0.safetensors",
55
+ "encoder.down_blocks.2.downsampler.resample_conv.weight": "0.safetensors",
56
+ "encoder.down_blocks.2.downsampler.resample_conv.bias": "0.safetensors",
57
+ "encoder.down_blocks.2.downsampler.time_conv.conv3d.weight": "0.safetensors",
58
+ "encoder.down_blocks.2.downsampler.time_conv.conv3d.bias": "0.safetensors",
59
+ "encoder.down_blocks.3.resnets.0.norm1.weight": "0.safetensors",
60
+ "encoder.down_blocks.3.resnets.0.conv1.conv3d.weight": "0.safetensors",
61
+ "encoder.down_blocks.3.resnets.0.conv1.conv3d.bias": "0.safetensors",
62
+ "encoder.down_blocks.3.resnets.0.norm2.weight": "0.safetensors",
63
+ "encoder.down_blocks.3.resnets.0.conv2.conv3d.weight": "0.safetensors",
64
+ "encoder.down_blocks.3.resnets.0.conv2.conv3d.bias": "0.safetensors",
65
+ "encoder.down_blocks.3.resnets.1.norm1.weight": "0.safetensors",
66
+ "encoder.down_blocks.3.resnets.1.conv1.conv3d.weight": "0.safetensors",
67
+ "encoder.down_blocks.3.resnets.1.conv1.conv3d.bias": "0.safetensors",
68
+ "encoder.down_blocks.3.resnets.1.norm2.weight": "0.safetensors",
69
+ "encoder.down_blocks.3.resnets.1.conv2.conv3d.weight": "0.safetensors",
70
+ "encoder.down_blocks.3.resnets.1.conv2.conv3d.bias": "0.safetensors",
71
+ "encoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
72
+ "encoder.mid_block.resnets.0.conv1.conv3d.weight": "0.safetensors",
73
+ "encoder.mid_block.resnets.0.conv1.conv3d.bias": "0.safetensors",
74
+ "encoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
75
+ "encoder.mid_block.resnets.0.conv2.conv3d.weight": "0.safetensors",
76
+ "encoder.mid_block.resnets.0.conv2.conv3d.bias": "0.safetensors",
77
+ "encoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
78
+ "encoder.mid_block.resnets.1.conv1.conv3d.weight": "0.safetensors",
79
+ "encoder.mid_block.resnets.1.conv1.conv3d.bias": "0.safetensors",
80
+ "encoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
81
+ "encoder.mid_block.resnets.1.conv2.conv3d.weight": "0.safetensors",
82
+ "encoder.mid_block.resnets.1.conv2.conv3d.bias": "0.safetensors",
83
+ "encoder.mid_block.attentions.0.norm.weight": "0.safetensors",
84
+ "encoder.mid_block.attentions.0.to_qkv.weight": "0.safetensors",
85
+ "encoder.mid_block.attentions.0.to_qkv.bias": "0.safetensors",
86
+ "encoder.mid_block.attentions.0.proj.weight": "0.safetensors",
87
+ "encoder.mid_block.attentions.0.proj.bias": "0.safetensors",
88
+ "encoder.norm_out.weight": "0.safetensors",
89
+ "encoder.conv_out.conv3d.weight": "0.safetensors",
90
+ "encoder.conv_out.conv3d.bias": "0.safetensors",
91
+ "quant_conv.conv3d.weight": "0.safetensors",
92
+ "quant_conv.conv3d.bias": "0.safetensors",
93
+ "post_quant_conv.conv3d.weight": "0.safetensors",
94
+ "post_quant_conv.conv3d.bias": "0.safetensors",
95
+ "decoder.conv_in.conv3d.weight": "0.safetensors",
96
+ "decoder.conv_in.conv3d.bias": "0.safetensors",
97
+ "decoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
98
+ "decoder.mid_block.resnets.0.conv1.conv3d.weight": "0.safetensors",
99
+ "decoder.mid_block.resnets.0.conv1.conv3d.bias": "0.safetensors",
100
+ "decoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
101
+ "decoder.mid_block.resnets.0.conv2.conv3d.weight": "0.safetensors",
102
+ "decoder.mid_block.resnets.0.conv2.conv3d.bias": "0.safetensors",
103
+ "decoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
104
+ "decoder.mid_block.resnets.1.conv1.conv3d.weight": "0.safetensors",
105
+ "decoder.mid_block.resnets.1.conv1.conv3d.bias": "0.safetensors",
106
+ "decoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
107
+ "decoder.mid_block.resnets.1.conv2.conv3d.weight": "0.safetensors",
108
+ "decoder.mid_block.resnets.1.conv2.conv3d.bias": "0.safetensors",
109
+ "decoder.mid_block.attentions.0.norm.weight": "0.safetensors",
110
+ "decoder.mid_block.attentions.0.to_qkv.weight": "0.safetensors",
111
+ "decoder.mid_block.attentions.0.to_qkv.bias": "0.safetensors",
112
+ "decoder.mid_block.attentions.0.proj.weight": "0.safetensors",
113
+ "decoder.mid_block.attentions.0.proj.bias": "0.safetensors",
114
+ "decoder.up_blocks.0.resnets.0.norm1.weight": "0.safetensors",
115
+ "decoder.up_blocks.0.resnets.0.conv1.conv3d.weight": "0.safetensors",
116
+ "decoder.up_blocks.0.resnets.0.conv1.conv3d.bias": "0.safetensors",
117
+ "decoder.up_blocks.0.resnets.0.norm2.weight": "0.safetensors",
118
+ "decoder.up_blocks.0.resnets.0.conv2.conv3d.weight": "0.safetensors",
119
+ "decoder.up_blocks.0.resnets.0.conv2.conv3d.bias": "0.safetensors",
120
+ "decoder.up_blocks.0.resnets.1.norm1.weight": "0.safetensors",
121
+ "decoder.up_blocks.0.resnets.1.conv1.conv3d.weight": "0.safetensors",
122
+ "decoder.up_blocks.0.resnets.1.conv1.conv3d.bias": "0.safetensors",
123
+ "decoder.up_blocks.0.resnets.1.norm2.weight": "0.safetensors",
124
+ "decoder.up_blocks.0.resnets.1.conv2.conv3d.weight": "0.safetensors",
125
+ "decoder.up_blocks.0.resnets.1.conv2.conv3d.bias": "0.safetensors",
126
+ "decoder.up_blocks.0.resnets.2.norm1.weight": "0.safetensors",
127
+ "decoder.up_blocks.0.resnets.2.conv1.conv3d.weight": "0.safetensors",
128
+ "decoder.up_blocks.0.resnets.2.conv1.conv3d.bias": "0.safetensors",
129
+ "decoder.up_blocks.0.resnets.2.norm2.weight": "0.safetensors",
130
+ "decoder.up_blocks.0.resnets.2.conv2.conv3d.weight": "0.safetensors",
131
+ "decoder.up_blocks.0.resnets.2.conv2.conv3d.bias": "0.safetensors",
132
+ "decoder.up_blocks.0.upsampler.time_conv.conv3d.weight": "0.safetensors",
133
+ "decoder.up_blocks.0.upsampler.time_conv.conv3d.bias": "0.safetensors",
134
+ "decoder.up_blocks.0.upsampler.resample_conv.weight": "0.safetensors",
135
+ "decoder.up_blocks.0.upsampler.resample_conv.bias": "0.safetensors",
136
+ "decoder.up_blocks.1.resnets.0.norm1.weight": "0.safetensors",
137
+ "decoder.up_blocks.1.resnets.0.conv1.conv3d.weight": "0.safetensors",
138
+ "decoder.up_blocks.1.resnets.0.conv1.conv3d.bias": "0.safetensors",
139
+ "decoder.up_blocks.1.resnets.0.norm2.weight": "0.safetensors",
140
+ "decoder.up_blocks.1.resnets.0.conv2.conv3d.weight": "0.safetensors",
141
+ "decoder.up_blocks.1.resnets.0.conv2.conv3d.bias": "0.safetensors",
142
+ "decoder.up_blocks.1.resnets.1.norm1.weight": "0.safetensors",
143
+ "decoder.up_blocks.1.resnets.1.conv1.conv3d.weight": "0.safetensors",
144
+ "decoder.up_blocks.1.resnets.1.conv1.conv3d.bias": "0.safetensors",
145
+ "decoder.up_blocks.1.resnets.1.norm2.weight": "0.safetensors",
146
+ "decoder.up_blocks.1.resnets.1.conv2.conv3d.weight": "0.safetensors",
147
+ "decoder.up_blocks.1.resnets.1.conv2.conv3d.bias": "0.safetensors",
148
+ "decoder.up_blocks.1.resnets.2.norm1.weight": "0.safetensors",
149
+ "decoder.up_blocks.1.resnets.2.conv1.conv3d.weight": "0.safetensors",
150
+ "decoder.up_blocks.1.resnets.2.conv1.conv3d.bias": "0.safetensors",
151
+ "decoder.up_blocks.1.resnets.2.norm2.weight": "0.safetensors",
152
+ "decoder.up_blocks.1.resnets.2.conv2.conv3d.weight": "0.safetensors",
153
+ "decoder.up_blocks.1.resnets.2.conv2.conv3d.bias": "0.safetensors",
154
+ "decoder.up_blocks.1.upsampler.time_conv.conv3d.weight": "0.safetensors",
155
+ "decoder.up_blocks.1.upsampler.time_conv.conv3d.bias": "0.safetensors",
156
+ "decoder.up_blocks.1.upsampler.resample_conv.weight": "0.safetensors",
157
+ "decoder.up_blocks.1.upsampler.resample_conv.bias": "0.safetensors",
158
+ "decoder.up_blocks.2.resnets.0.norm1.weight": "0.safetensors",
159
+ "decoder.up_blocks.2.resnets.0.conv1.conv3d.weight": "0.safetensors",
160
+ "decoder.up_blocks.2.resnets.0.conv1.conv3d.bias": "0.safetensors",
161
+ "decoder.up_blocks.2.resnets.0.norm2.weight": "0.safetensors",
162
+ "decoder.up_blocks.2.resnets.0.conv2.conv3d.weight": "0.safetensors",
163
+ "decoder.up_blocks.2.resnets.0.conv2.conv3d.bias": "0.safetensors",
164
+ "decoder.up_blocks.2.resnets.0.conv_shortcut.conv3d.weight": "0.safetensors",
165
+ "decoder.up_blocks.2.resnets.0.conv_shortcut.conv3d.bias": "0.safetensors",
166
+ "decoder.up_blocks.2.resnets.1.norm1.weight": "0.safetensors",
167
+ "decoder.up_blocks.2.resnets.1.conv1.conv3d.weight": "0.safetensors",
168
+ "decoder.up_blocks.2.resnets.1.conv1.conv3d.bias": "0.safetensors",
169
+ "decoder.up_blocks.2.resnets.1.norm2.weight": "0.safetensors",
170
+ "decoder.up_blocks.2.resnets.1.conv2.conv3d.weight": "0.safetensors",
171
+ "decoder.up_blocks.2.resnets.1.conv2.conv3d.bias": "0.safetensors",
172
+ "decoder.up_blocks.2.resnets.2.norm1.weight": "0.safetensors",
173
+ "decoder.up_blocks.2.resnets.2.conv1.conv3d.weight": "0.safetensors",
174
+ "decoder.up_blocks.2.resnets.2.conv1.conv3d.bias": "0.safetensors",
175
+ "decoder.up_blocks.2.resnets.2.norm2.weight": "0.safetensors",
176
+ "decoder.up_blocks.2.resnets.2.conv2.conv3d.weight": "0.safetensors",
177
+ "decoder.up_blocks.2.resnets.2.conv2.conv3d.bias": "0.safetensors",
178
+ "decoder.up_blocks.2.upsampler.resample_conv.weight": "0.safetensors",
179
+ "decoder.up_blocks.2.upsampler.resample_conv.bias": "0.safetensors",
180
+ "decoder.up_blocks.3.resnets.0.norm1.weight": "0.safetensors",
181
+ "decoder.up_blocks.3.resnets.0.conv1.conv3d.weight": "0.safetensors",
182
+ "decoder.up_blocks.3.resnets.0.conv1.conv3d.bias": "0.safetensors",
183
+ "decoder.up_blocks.3.resnets.0.norm2.weight": "0.safetensors",
184
+ "decoder.up_blocks.3.resnets.0.conv2.conv3d.weight": "0.safetensors",
185
+ "decoder.up_blocks.3.resnets.0.conv2.conv3d.bias": "0.safetensors",
186
+ "decoder.up_blocks.3.resnets.0.conv_shortcut.conv3d.weight": "0.safetensors",
187
+ "decoder.up_blocks.3.resnets.0.conv_shortcut.conv3d.bias": "0.safetensors",
188
+ "decoder.up_blocks.3.resnets.1.norm1.weight": "0.safetensors",
189
+ "decoder.up_blocks.3.resnets.1.conv1.conv3d.weight": "0.safetensors",
190
+ "decoder.up_blocks.3.resnets.1.conv1.conv3d.bias": "0.safetensors",
191
+ "decoder.up_blocks.3.resnets.1.norm2.weight": "0.safetensors",
192
+ "decoder.up_blocks.3.resnets.1.conv2.conv3d.weight": "0.safetensors",
193
+ "decoder.up_blocks.3.resnets.1.conv2.conv3d.bias": "0.safetensors",
194
+ "decoder.up_blocks.3.resnets.2.norm1.weight": "0.safetensors",
195
+ "decoder.up_blocks.3.resnets.2.conv1.conv3d.weight": "0.safetensors",
196
+ "decoder.up_blocks.3.resnets.2.conv1.conv3d.bias": "0.safetensors",
197
+ "decoder.up_blocks.3.resnets.2.norm2.weight": "0.safetensors",
198
+ "decoder.up_blocks.3.resnets.2.conv2.conv3d.weight": "0.safetensors",
199
+ "decoder.up_blocks.3.resnets.2.conv2.conv3d.bias": "0.safetensors",
200
+ "decoder.norm_out.weight": "0.safetensors",
201
+ "decoder.conv_out.conv3d.weight": "0.safetensors",
202
+ "decoder.conv_out.conv3d.bias": "0.safetensors"
203
+ }
204
+ }