Hugging Face's logo

mikoy92
/
MiniMax-Music3-MLX-8bit

Text-to-Audio
MLX
Diffusers
Safetensors
apple-silicon
music-generation
8-bit precision
Model card Files
xet
 Community
mikoy92 commited on
Commit
fa13130
·
verified ·
1 Parent(s): 795e34c

Add configs, tokenizer, README

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. README.md +25 -0
  3. condition_encoder/config.json +11 -0
  4. language_model/config.json +71 -0
  5. language_model/generation_config.json +7 -0
  6. language_model/model.safetensors.index.json +912 -0
  7. mlx_config.json +14 -0
  8. modular_model_index.json +103 -0
  9. rvq_depth_decoder/config.json +11 -0
  10. rvq_depth_decoder/diffusion_pytorch_model.safetensors.index.json +126 -0
  11. scheduler/scheduler_config.json +18 -0
  12. tokenizer/chat_template.jinja +89 -0
  13. tokenizer/tokenizer.json +3 -0
  14. tokenizer/tokenizer_config.json +15 -0
  15. transformer/config.json +12 -0
  16. transformer/diffusion_pytorch_model.safetensors.index.json +888 -0
  17. vocoder/config.json +14 -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 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: minimax-music3-community
4
+ license_link: https://huggingface.co/MiniMaxAI/MiniMax-Music3
5
+ base_model: MiniMaxAI/MiniMax-Music3
6
+ library_name: mlx
7
+ pipeline_tag: text-to-audio
8
+ tags:
9
+ - mlx
10
+ - apple-silicon
11
+ - music-generation
12
+ - 8-bit
13
+ ---
14
+
15
+ # MiniMax Music 3 — MLX 8-bit
16
+
17
+ 8-bit quantized Linear layers (`group_size=64`) of [MiniMaxAI/MiniMax-Music3](https://huggingface.co/MiniMaxAI/MiniMax-Music3) for [mikolaj92/minimax-music3-mlx](https://github.com/mikolaj92/minimax-music3-mlx). Vocoder and condition encoder stay bf16.
18
+
19
+ ```bash
20
+ hf download mikoy92/MiniMax-Music3-MLX-8bit --local-dir ./weights/mlx-8bit
21
+ python -m minimax_music3_mlx.generate --weights ./weights/mlx-8bit \
22
+ --lyrics $'[verse]\n...\n[chorus]\n...' --prompt "..." --duration 30 --steps 30 --output song.wav
23
+ ```
24
+
25
+ Weights remain under the [MiniMax-Music3 Community License](https://huggingface.co/MiniMaxAI/MiniMax-Music3).
condition_encoder/config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MiniMaxMusic3ConditionEncoder",
3
+ "_diffusers_version": "0.40.0.dev0",
4
+ "condition_hidden_dim": 4096,
5
+ "input_hop_length": 960,
6
+ "input_sampling_rate": 24000,
7
+ "num_condition_layers": 8,
8
+ "out_dim": 2048,
9
+ "output_hop_length": 512,
10
+ "output_sampling_rate": 44100
11
+ }
language_model/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": null,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12288,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 10240,
54
+ "max_window_layers": 28,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "pad_token_id": null,
60
+ "rms_norm_eps": 1e-06,
61
+ "rope_parameters": {
62
+ "rope_theta": 1000000,
63
+ "rope_type": "default"
64
+ },
65
+ "sliding_window": null,
66
+ "tie_word_embeddings": false,
67
+ "transformers_version": "5.13.0.dev0",
68
+ "use_cache": true,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 200000
71
+ }
language_model/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.13.0.dev0",
6
+ "use_cache": true
7
+ }
language_model/model.safetensors.index.json ADDED
@@ -0,0 +1,912 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 9889294336
4
+ },
5
+ "weight_map": {
6
+ "lm_head.biases": "model-00002-of-00002.safetensors",
7
+ "lm_head.scales": "model-00002-of-00002.safetensors",
8
+ "lm_head.weight": "model-00002-of-00002.safetensors",
9
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
31
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
33
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
34
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
55
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
56
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
58
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
59
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
62
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
63
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
65
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
66
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
68
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
69
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
76
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
77
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
80
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
81
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
83
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
84
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
87
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
88
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
90
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
91
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
93
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
94
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
98
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
99
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
101
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
102
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
105
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
106
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
108
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
109
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
112
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
113
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
115
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
116
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
118
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
119
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
123
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
124
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
126
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
127
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
130
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
131
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
133
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
134
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
137
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
138
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
140
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
141
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
143
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
144
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
148
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
149
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
151
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
152
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
155
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
156
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
158
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
159
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
162
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
163
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
165
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
166
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
168
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
169
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
173
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
174
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
176
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
177
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
180
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
181
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
183
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
184
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
187
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
188
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
190
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
191
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
193
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
194
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
198
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
199
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
201
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
202
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
205
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
206
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
208
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
209
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
212
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
213
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
215
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
216
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
218
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
219
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
223
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
224
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
226
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
227
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
230
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
231
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
233
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
234
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
237
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
238
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
240
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
241
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
243
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
244
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
248
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
249
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
251
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
252
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
255
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
256
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
258
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
259
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
262
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
263
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
265
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
266
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
268
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
269
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
273
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
274
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
276
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
277
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
280
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
281
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
283
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
284
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
287
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
288
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
290
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
291
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
293
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
294
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
298
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
299
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
301
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
302
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
305
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
306
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
308
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
309
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
312
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
313
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
315
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
316
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
318
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
319
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
323
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
324
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
326
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
327
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
330
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
331
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
333
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
334
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
337
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
338
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
340
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
341
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
343
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
344
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
348
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
349
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
351
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
352
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
355
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
356
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
358
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
359
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
362
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
363
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
365
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
366
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
368
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
369
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
370
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
372
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
373
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
374
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
376
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
377
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
378
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
379
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
380
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
381
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
382
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
383
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
384
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
385
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
386
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
387
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
388
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
389
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
390
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
391
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
392
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
393
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
394
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
395
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
396
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
397
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
398
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
399
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
400
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
401
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
402
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
403
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
404
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
405
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
406
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
407
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
408
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
409
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
410
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
411
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
412
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
413
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
414
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
415
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
416
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
417
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
418
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
419
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
420
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
421
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
422
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
423
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
424
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
425
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
426
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
427
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
428
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
429
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
430
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
431
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
432
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
433
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
434
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
435
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
436
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
437
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
438
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
439
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
440
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
441
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
442
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
443
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
444
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
445
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
446
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
447
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
448
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
449
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
450
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
451
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
452
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
453
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
454
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
455
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
456
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
457
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
458
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
459
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
460
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
461
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
462
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
463
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
464
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
465
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
466
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
467
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
468
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
469
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
470
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
471
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
472
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
473
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
474
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
475
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
476
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
477
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
478
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
479
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
480
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
481
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
482
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
483
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
484
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
485
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
486
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
487
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
488
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
489
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
490
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
491
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
492
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
493
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
494
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
495
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
496
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
497
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
498
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
499
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
500
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
501
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
502
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
503
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
504
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
505
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
506
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
507
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
508
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
509
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
510
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
511
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
512
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
513
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
514
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
515
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
516
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
517
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
518
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
519
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
520
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
521
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
522
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
523
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
524
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
525
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
526
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
527
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
528
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
529
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
530
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
531
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
532
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
533
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
534
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
535
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
536
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
537
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
538
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
539
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
540
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
541
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
542
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
543
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
544
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
545
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
546
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
547
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
548
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
549
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
550
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
551
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
552
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
553
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
554
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
555
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
556
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
557
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
558
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
559
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
560
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
561
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
562
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
563
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
564
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
565
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
566
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
567
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
568
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
569
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
570
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
571
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
572
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
573
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
574
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
575
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
576
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
577
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
578
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
579
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
580
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
581
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
582
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
583
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
584
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
585
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
586
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
587
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
588
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
589
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
590
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
591
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
592
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
593
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
594
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
595
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
596
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
597
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
598
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
599
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
600
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
601
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
602
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
603
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
604
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
605
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
606
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
607
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
608
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
609
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
610
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
611
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
612
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
613
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
614
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
615
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
616
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
617
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
618
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
619
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
620
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
621
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
622
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
623
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
624
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
625
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
626
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
627
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
628
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
629
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
630
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
631
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
632
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
633
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
634
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
635
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
636
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
637
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
638
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
639
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
640
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
641
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
642
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
643
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
644
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
645
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
646
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
647
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
648
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
649
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
650
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
651
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
652
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
653
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
654
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
655
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
656
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
657
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
658
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
659
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
660
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
661
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
662
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
663
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
664
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
665
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
666
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
667
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
668
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
669
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
670
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
671
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
672
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
673
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
674
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
675
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
676
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
677
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
678
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
679
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
680
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
681
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
682
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
683
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
684
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
685
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
686
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
687
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
688
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
689
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
690
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
691
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
692
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
693
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
694
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
695
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
696
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
697
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
698
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
699
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
700
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
701
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
702
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
703
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
704
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
705
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
706
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
707
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
708
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
709
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
710
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
711
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
712
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
713
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
714
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
715
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
716
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
717
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
718
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
719
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
720
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
721
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
722
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
723
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
724
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
725
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
726
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
727
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
728
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
729
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
730
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
731
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
732
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
733
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
734
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
735
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
736
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
737
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
738
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
739
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
740
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
741
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
742
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
743
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
744
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
745
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
746
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
747
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
748
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
749
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
750
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
751
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
752
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
753
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
754
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
755
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
756
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
757
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
758
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
759
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
760
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
761
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
762
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
763
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
764
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
765
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
766
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
767
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
768
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
769
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
770
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
771
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
772
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
773
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
774
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
775
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
776
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
777
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
778
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
779
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
780
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
781
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
782
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
783
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
784
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
785
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
786
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
787
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
788
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
789
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
790
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
791
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
792
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
793
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
794
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
795
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
796
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
797
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
798
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
799
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
800
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
801
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
802
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
803
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
804
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
805
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
806
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
807
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
808
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
809
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
810
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
811
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
812
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
813
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
814
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
815
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
816
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
817
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
818
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
819
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
820
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
821
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
822
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
823
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
824
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
825
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
826
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
827
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
828
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
829
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
830
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
831
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
832
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
833
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
834
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
835
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
836
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
837
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
838
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
839
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
840
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
841
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
842
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
843
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
844
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
845
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
846
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
847
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
848
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
849
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
850
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
851
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
852
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
853
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
854
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
855
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
856
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
857
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
858
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
859
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
860
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
861
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
862
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
863
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
864
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
865
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
866
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
867
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
868
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
869
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
870
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
871
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
872
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
873
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
874
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
875
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
876
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
877
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
878
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
879
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
880
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
881
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
882
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
883
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
884
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
885
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
886
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
887
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
888
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
889
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
890
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
891
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
892
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
893
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
894
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
895
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
896
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
897
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
898
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
899
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
900
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
901
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
902
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
903
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
904
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
905
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
906
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
907
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
908
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
909
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
910
+ "model.norm.weight": "model-00002-of-00002.safetensors"
911
+ }
912
+ }
mlx_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "format": "mlx",
3
+ "source": "MiniMax-Music3",
4
+ "layout": "minimax-music3-diffusers",
5
+ "quantized": true,
6
+ "bits": 8,
7
+ "group_size": 64,
8
+ "mode": "affine",
9
+ "quantize_modules": [
10
+ "language_model",
11
+ "transformer",
12
+ "rvq_depth_decoder"
13
+ ]
14
+ }
modular_model_index.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_blocks_class_name": "MiniMaxMusic3Blocks",
3
+ "_class_name": "MiniMaxMusic3ModularPipeline",
4
+ "_diffusers_version": "0.40.0.dev0",
5
+ "condition_encoder": [
6
+ "diffusers",
7
+ "MiniMaxMusic3ConditionEncoder",
8
+ {
9
+ "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-Music3",
10
+ "revision": null,
11
+ "subfolder": "condition_encoder",
12
+ "type_hint": [
13
+ "diffusers",
14
+ "MiniMaxMusic3ConditionEncoder"
15
+ ],
16
+ "variant": null
17
+ }
18
+ ],
19
+ "language_model": [
20
+ "transformers",
21
+ "Qwen3ForCausalLM",
22
+ {
23
+ "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-Music3",
24
+ "revision": null,
25
+ "subfolder": "language_model",
26
+ "type_hint": [
27
+ "transformers",
28
+ "Qwen3ForCausalLM"
29
+ ],
30
+ "variant": null
31
+ }
32
+ ],
33
+ "rvq_depth_decoder": [
34
+ "diffusers",
35
+ "MiniMaxMusic3RVQDepthDecoder",
36
+ {
37
+ "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-Music3",
38
+ "revision": null,
39
+ "subfolder": "rvq_depth_decoder",
40
+ "type_hint": [
41
+ "diffusers",
42
+ "MiniMaxMusic3RVQDepthDecoder"
43
+ ],
44
+ "variant": null
45
+ }
46
+ ],
47
+ "scheduler": [
48
+ "diffusers",
49
+ "FlowMatchEulerDiscreteScheduler",
50
+ {
51
+ "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-Music3",
52
+ "revision": null,
53
+ "subfolder": "scheduler",
54
+ "type_hint": [
55
+ "diffusers",
56
+ "FlowMatchEulerDiscreteScheduler"
57
+ ],
58
+ "variant": null
59
+ }
60
+ ],
61
+ "tokenizer": [
62
+ "transformers",
63
+ "Qwen2Tokenizer",
64
+ {
65
+ "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-Music3",
66
+ "revision": null,
67
+ "subfolder": "tokenizer",
68
+ "type_hint": [
69
+ "transformers",
70
+ "Qwen2Tokenizer"
71
+ ],
72
+ "variant": null
73
+ }
74
+ ],
75
+ "transformer": [
76
+ "diffusers",
77
+ "MiniMaxMusic3Transformer1DModel",
78
+ {
79
+ "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-Music3",
80
+ "revision": null,
81
+ "subfolder": "transformer",
82
+ "type_hint": [
83
+ "diffusers",
84
+ "MiniMaxMusic3Transformer1DModel"
85
+ ],
86
+ "variant": null
87
+ }
88
+ ],
89
+ "vocoder": [
90
+ "diffusers",
91
+ "MiniMaxMusic3Vocoder",
92
+ {
93
+ "pretrained_model_name_or_path": "MiniMaxAI/MiniMax-Music3",
94
+ "revision": null,
95
+ "subfolder": "vocoder",
96
+ "type_hint": [
97
+ "diffusers",
98
+ "MiniMaxMusic3Vocoder"
99
+ ],
100
+ "variant": null
101
+ }
102
+ ]
103
+ }
rvq_depth_decoder/config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MiniMaxMusic3RVQDepthDecoder",
3
+ "_diffusers_version": "0.40.0.dev0",
4
+ "audio_vocab_size": 1024,
5
+ "hidden_size": 4096,
6
+ "intermediate_size": 6144,
7
+ "max_position_embeddings": 16,
8
+ "num_attention_heads": 16,
9
+ "num_codebooks": 8,
10
+ "num_layers": 4
11
+ }
rvq_depth_decoder/diffusion_pytorch_model.safetensors.index.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 714022912
4
+ },
5
+ "weight_map": {
6
+ "audio_embeddings.weight": "diffusion_pytorch_model.safetensors",
7
+ "audio_heads.0.biases": "diffusion_pytorch_model.safetensors",
8
+ "audio_heads.0.scales": "diffusion_pytorch_model.safetensors",
9
+ "audio_heads.0.weight": "diffusion_pytorch_model.safetensors",
10
+ "audio_heads.1.biases": "diffusion_pytorch_model.safetensors",
11
+ "audio_heads.1.scales": "diffusion_pytorch_model.safetensors",
12
+ "audio_heads.1.weight": "diffusion_pytorch_model.safetensors",
13
+ "audio_heads.2.biases": "diffusion_pytorch_model.safetensors",
14
+ "audio_heads.2.scales": "diffusion_pytorch_model.safetensors",
15
+ "audio_heads.2.weight": "diffusion_pytorch_model.safetensors",
16
+ "audio_heads.3.biases": "diffusion_pytorch_model.safetensors",
17
+ "audio_heads.3.scales": "diffusion_pytorch_model.safetensors",
18
+ "audio_heads.3.weight": "diffusion_pytorch_model.safetensors",
19
+ "audio_heads.4.biases": "diffusion_pytorch_model.safetensors",
20
+ "audio_heads.4.scales": "diffusion_pytorch_model.safetensors",
21
+ "audio_heads.4.weight": "diffusion_pytorch_model.safetensors",
22
+ "audio_heads.5.biases": "diffusion_pytorch_model.safetensors",
23
+ "audio_heads.5.scales": "diffusion_pytorch_model.safetensors",
24
+ "audio_heads.5.weight": "diffusion_pytorch_model.safetensors",
25
+ "audio_heads.6.biases": "diffusion_pytorch_model.safetensors",
26
+ "audio_heads.6.scales": "diffusion_pytorch_model.safetensors",
27
+ "audio_heads.6.weight": "diffusion_pytorch_model.safetensors",
28
+ "layers.0.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
29
+ "layers.0.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
30
+ "layers.0.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
31
+ "layers.0.attn.to_out.biases": "diffusion_pytorch_model.safetensors",
32
+ "layers.0.attn.to_out.scales": "diffusion_pytorch_model.safetensors",
33
+ "layers.0.attn.to_out.weight": "diffusion_pytorch_model.safetensors",
34
+ "layers.0.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
35
+ "layers.0.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
36
+ "layers.0.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
37
+ "layers.0.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
38
+ "layers.0.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
39
+ "layers.0.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
40
+ "layers.0.down_proj.biases": "diffusion_pytorch_model.safetensors",
41
+ "layers.0.down_proj.scales": "diffusion_pytorch_model.safetensors",
42
+ "layers.0.down_proj.weight": "diffusion_pytorch_model.safetensors",
43
+ "layers.0.gate_proj.biases": "diffusion_pytorch_model.safetensors",
44
+ "layers.0.gate_proj.scales": "diffusion_pytorch_model.safetensors",
45
+ "layers.0.gate_proj.weight": "diffusion_pytorch_model.safetensors",
46
+ "layers.0.input_layernorm.weight": "diffusion_pytorch_model.safetensors",
47
+ "layers.0.post_attention_layernorm.weight": "diffusion_pytorch_model.safetensors",
48
+ "layers.0.up_proj.biases": "diffusion_pytorch_model.safetensors",
49
+ "layers.0.up_proj.scales": "diffusion_pytorch_model.safetensors",
50
+ "layers.0.up_proj.weight": "diffusion_pytorch_model.safetensors",
51
+ "layers.1.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
52
+ "layers.1.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
53
+ "layers.1.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
54
+ "layers.1.attn.to_out.biases": "diffusion_pytorch_model.safetensors",
55
+ "layers.1.attn.to_out.scales": "diffusion_pytorch_model.safetensors",
56
+ "layers.1.attn.to_out.weight": "diffusion_pytorch_model.safetensors",
57
+ "layers.1.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
58
+ "layers.1.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
59
+ "layers.1.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
60
+ "layers.1.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
61
+ "layers.1.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
62
+ "layers.1.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
63
+ "layers.1.down_proj.biases": "diffusion_pytorch_model.safetensors",
64
+ "layers.1.down_proj.scales": "diffusion_pytorch_model.safetensors",
65
+ "layers.1.down_proj.weight": "diffusion_pytorch_model.safetensors",
66
+ "layers.1.gate_proj.biases": "diffusion_pytorch_model.safetensors",
67
+ "layers.1.gate_proj.scales": "diffusion_pytorch_model.safetensors",
68
+ "layers.1.gate_proj.weight": "diffusion_pytorch_model.safetensors",
69
+ "layers.1.input_layernorm.weight": "diffusion_pytorch_model.safetensors",
70
+ "layers.1.post_attention_layernorm.weight": "diffusion_pytorch_model.safetensors",
71
+ "layers.1.up_proj.biases": "diffusion_pytorch_model.safetensors",
72
+ "layers.1.up_proj.scales": "diffusion_pytorch_model.safetensors",
73
+ "layers.1.up_proj.weight": "diffusion_pytorch_model.safetensors",
74
+ "layers.2.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
75
+ "layers.2.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
76
+ "layers.2.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
77
+ "layers.2.attn.to_out.biases": "diffusion_pytorch_model.safetensors",
78
+ "layers.2.attn.to_out.scales": "diffusion_pytorch_model.safetensors",
79
+ "layers.2.attn.to_out.weight": "diffusion_pytorch_model.safetensors",
80
+ "layers.2.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
81
+ "layers.2.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
82
+ "layers.2.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
83
+ "layers.2.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
84
+ "layers.2.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
85
+ "layers.2.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
86
+ "layers.2.down_proj.biases": "diffusion_pytorch_model.safetensors",
87
+ "layers.2.down_proj.scales": "diffusion_pytorch_model.safetensors",
88
+ "layers.2.down_proj.weight": "diffusion_pytorch_model.safetensors",
89
+ "layers.2.gate_proj.biases": "diffusion_pytorch_model.safetensors",
90
+ "layers.2.gate_proj.scales": "diffusion_pytorch_model.safetensors",
91
+ "layers.2.gate_proj.weight": "diffusion_pytorch_model.safetensors",
92
+ "layers.2.input_layernorm.weight": "diffusion_pytorch_model.safetensors",
93
+ "layers.2.post_attention_layernorm.weight": "diffusion_pytorch_model.safetensors",
94
+ "layers.2.up_proj.biases": "diffusion_pytorch_model.safetensors",
95
+ "layers.2.up_proj.scales": "diffusion_pytorch_model.safetensors",
96
+ "layers.2.up_proj.weight": "diffusion_pytorch_model.safetensors",
97
+ "layers.3.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
98
+ "layers.3.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
99
+ "layers.3.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
100
+ "layers.3.attn.to_out.biases": "diffusion_pytorch_model.safetensors",
101
+ "layers.3.attn.to_out.scales": "diffusion_pytorch_model.safetensors",
102
+ "layers.3.attn.to_out.weight": "diffusion_pytorch_model.safetensors",
103
+ "layers.3.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
104
+ "layers.3.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
105
+ "layers.3.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
106
+ "layers.3.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
107
+ "layers.3.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
108
+ "layers.3.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
109
+ "layers.3.down_proj.biases": "diffusion_pytorch_model.safetensors",
110
+ "layers.3.down_proj.scales": "diffusion_pytorch_model.safetensors",
111
+ "layers.3.down_proj.weight": "diffusion_pytorch_model.safetensors",
112
+ "layers.3.gate_proj.biases": "diffusion_pytorch_model.safetensors",
113
+ "layers.3.gate_proj.scales": "diffusion_pytorch_model.safetensors",
114
+ "layers.3.gate_proj.weight": "diffusion_pytorch_model.safetensors",
115
+ "layers.3.input_layernorm.weight": "diffusion_pytorch_model.safetensors",
116
+ "layers.3.post_attention_layernorm.weight": "diffusion_pytorch_model.safetensors",
117
+ "layers.3.up_proj.biases": "diffusion_pytorch_model.safetensors",
118
+ "layers.3.up_proj.scales": "diffusion_pytorch_model.safetensors",
119
+ "layers.3.up_proj.weight": "diffusion_pytorch_model.safetensors",
120
+ "norm.weight": "diffusion_pytorch_model.safetensors",
121
+ "pos_embedding.weight": "diffusion_pytorch_model.safetensors",
122
+ "projection.biases": "diffusion_pytorch_model.safetensors",
123
+ "projection.scales": "diffusion_pytorch_model.safetensors",
124
+ "projection.weight": "diffusion_pytorch_model.safetensors"
125
+ }
126
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.40.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": true,
7
+ "max_image_seq_len": 4096,
8
+ "max_shift": 1.15,
9
+ "num_train_timesteps": 1,
10
+ "shift": 1.0,
11
+ "shift_terminal": null,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": false,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1537fa9e59a537276ecbc2e12d0438edff635a1f4a4948e679774b5feb3e610
3
+ size 11423801
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "local_files_only": false,
10
+ "model_max_length": 131072,
11
+ "pad_token": "<|endoftext|>",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "Qwen2Tokenizer",
14
+ "unk_token": null
15
+ }
transformer/config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MiniMaxMusic3Transformer1DModel",
3
+ "_diffusers_version": "0.40.0.dev0",
4
+ "attention_head_dim": 64,
5
+ "condition_dim": 2048,
6
+ "ff_inner_dim": 8192,
7
+ "fourier_embedding_dim": 256,
8
+ "in_channels": 128,
9
+ "num_attention_heads": 32,
10
+ "num_layers": 36,
11
+ "rotary_dim": 32
12
+ }
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
@@ -0,0 +1,888 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2589794560
4
+ },
5
+ "weight_map": {
6
+ "postprocess_conv.weight": "diffusion_pytorch_model.safetensors",
7
+ "preprocess_conv.weight": "diffusion_pytorch_model.safetensors",
8
+ "proj_in.biases": "diffusion_pytorch_model.safetensors",
9
+ "proj_in.scales": "diffusion_pytorch_model.safetensors",
10
+ "proj_in.weight": "diffusion_pytorch_model.safetensors",
11
+ "proj_out.biases": "diffusion_pytorch_model.safetensors",
12
+ "proj_out.scales": "diffusion_pytorch_model.safetensors",
13
+ "proj_out.weight": "diffusion_pytorch_model.safetensors",
14
+ "time_embed.linear_1.bias": "diffusion_pytorch_model.safetensors",
15
+ "time_embed.linear_1.biases": "diffusion_pytorch_model.safetensors",
16
+ "time_embed.linear_1.scales": "diffusion_pytorch_model.safetensors",
17
+ "time_embed.linear_1.weight": "diffusion_pytorch_model.safetensors",
18
+ "time_embed.linear_2.bias": "diffusion_pytorch_model.safetensors",
19
+ "time_embed.linear_2.biases": "diffusion_pytorch_model.safetensors",
20
+ "time_embed.linear_2.scales": "diffusion_pytorch_model.safetensors",
21
+ "time_embed.linear_2.weight": "diffusion_pytorch_model.safetensors",
22
+ "time_proj.weight": "diffusion_pytorch_model.safetensors",
23
+ "transformer_blocks.0.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
24
+ "transformer_blocks.0.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
25
+ "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
26
+ "transformer_blocks.0.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
27
+ "transformer_blocks.0.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
28
+ "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
29
+ "transformer_blocks.0.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
30
+ "transformer_blocks.0.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
31
+ "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
32
+ "transformer_blocks.0.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
33
+ "transformer_blocks.0.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
34
+ "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
35
+ "transformer_blocks.0.ff_in.bias": "diffusion_pytorch_model.safetensors",
36
+ "transformer_blocks.0.ff_in.biases": "diffusion_pytorch_model.safetensors",
37
+ "transformer_blocks.0.ff_in.scales": "diffusion_pytorch_model.safetensors",
38
+ "transformer_blocks.0.ff_in.weight": "diffusion_pytorch_model.safetensors",
39
+ "transformer_blocks.0.ff_out.bias": "diffusion_pytorch_model.safetensors",
40
+ "transformer_blocks.0.ff_out.biases": "diffusion_pytorch_model.safetensors",
41
+ "transformer_blocks.0.ff_out.scales": "diffusion_pytorch_model.safetensors",
42
+ "transformer_blocks.0.ff_out.weight": "diffusion_pytorch_model.safetensors",
43
+ "transformer_blocks.0.norm1.bias": "diffusion_pytorch_model.safetensors",
44
+ "transformer_blocks.0.norm1.weight": "diffusion_pytorch_model.safetensors",
45
+ "transformer_blocks.0.norm2.bias": "diffusion_pytorch_model.safetensors",
46
+ "transformer_blocks.0.norm2.weight": "diffusion_pytorch_model.safetensors",
47
+ "transformer_blocks.1.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
48
+ "transformer_blocks.1.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
49
+ "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
50
+ "transformer_blocks.1.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
51
+ "transformer_blocks.1.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
52
+ "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
53
+ "transformer_blocks.1.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
54
+ "transformer_blocks.1.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
55
+ "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
56
+ "transformer_blocks.1.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
57
+ "transformer_blocks.1.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
58
+ "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
59
+ "transformer_blocks.1.ff_in.bias": "diffusion_pytorch_model.safetensors",
60
+ "transformer_blocks.1.ff_in.biases": "diffusion_pytorch_model.safetensors",
61
+ "transformer_blocks.1.ff_in.scales": "diffusion_pytorch_model.safetensors",
62
+ "transformer_blocks.1.ff_in.weight": "diffusion_pytorch_model.safetensors",
63
+ "transformer_blocks.1.ff_out.bias": "diffusion_pytorch_model.safetensors",
64
+ "transformer_blocks.1.ff_out.biases": "diffusion_pytorch_model.safetensors",
65
+ "transformer_blocks.1.ff_out.scales": "diffusion_pytorch_model.safetensors",
66
+ "transformer_blocks.1.ff_out.weight": "diffusion_pytorch_model.safetensors",
67
+ "transformer_blocks.1.norm1.bias": "diffusion_pytorch_model.safetensors",
68
+ "transformer_blocks.1.norm1.weight": "diffusion_pytorch_model.safetensors",
69
+ "transformer_blocks.1.norm2.bias": "diffusion_pytorch_model.safetensors",
70
+ "transformer_blocks.1.norm2.weight": "diffusion_pytorch_model.safetensors",
71
+ "transformer_blocks.10.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
72
+ "transformer_blocks.10.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
73
+ "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
74
+ "transformer_blocks.10.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
75
+ "transformer_blocks.10.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
76
+ "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
77
+ "transformer_blocks.10.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
78
+ "transformer_blocks.10.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
79
+ "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
80
+ "transformer_blocks.10.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
81
+ "transformer_blocks.10.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
82
+ "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
83
+ "transformer_blocks.10.ff_in.bias": "diffusion_pytorch_model.safetensors",
84
+ "transformer_blocks.10.ff_in.biases": "diffusion_pytorch_model.safetensors",
85
+ "transformer_blocks.10.ff_in.scales": "diffusion_pytorch_model.safetensors",
86
+ "transformer_blocks.10.ff_in.weight": "diffusion_pytorch_model.safetensors",
87
+ "transformer_blocks.10.ff_out.bias": "diffusion_pytorch_model.safetensors",
88
+ "transformer_blocks.10.ff_out.biases": "diffusion_pytorch_model.safetensors",
89
+ "transformer_blocks.10.ff_out.scales": "diffusion_pytorch_model.safetensors",
90
+ "transformer_blocks.10.ff_out.weight": "diffusion_pytorch_model.safetensors",
91
+ "transformer_blocks.10.norm1.bias": "diffusion_pytorch_model.safetensors",
92
+ "transformer_blocks.10.norm1.weight": "diffusion_pytorch_model.safetensors",
93
+ "transformer_blocks.10.norm2.bias": "diffusion_pytorch_model.safetensors",
94
+ "transformer_blocks.10.norm2.weight": "diffusion_pytorch_model.safetensors",
95
+ "transformer_blocks.11.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
96
+ "transformer_blocks.11.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
97
+ "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
98
+ "transformer_blocks.11.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
99
+ "transformer_blocks.11.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
100
+ "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
101
+ "transformer_blocks.11.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
102
+ "transformer_blocks.11.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
103
+ "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
104
+ "transformer_blocks.11.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
105
+ "transformer_blocks.11.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
106
+ "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
107
+ "transformer_blocks.11.ff_in.bias": "diffusion_pytorch_model.safetensors",
108
+ "transformer_blocks.11.ff_in.biases": "diffusion_pytorch_model.safetensors",
109
+ "transformer_blocks.11.ff_in.scales": "diffusion_pytorch_model.safetensors",
110
+ "transformer_blocks.11.ff_in.weight": "diffusion_pytorch_model.safetensors",
111
+ "transformer_blocks.11.ff_out.bias": "diffusion_pytorch_model.safetensors",
112
+ "transformer_blocks.11.ff_out.biases": "diffusion_pytorch_model.safetensors",
113
+ "transformer_blocks.11.ff_out.scales": "diffusion_pytorch_model.safetensors",
114
+ "transformer_blocks.11.ff_out.weight": "diffusion_pytorch_model.safetensors",
115
+ "transformer_blocks.11.norm1.bias": "diffusion_pytorch_model.safetensors",
116
+ "transformer_blocks.11.norm1.weight": "diffusion_pytorch_model.safetensors",
117
+ "transformer_blocks.11.norm2.bias": "diffusion_pytorch_model.safetensors",
118
+ "transformer_blocks.11.norm2.weight": "diffusion_pytorch_model.safetensors",
119
+ "transformer_blocks.12.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
120
+ "transformer_blocks.12.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
121
+ "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
122
+ "transformer_blocks.12.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
123
+ "transformer_blocks.12.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
124
+ "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
125
+ "transformer_blocks.12.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
126
+ "transformer_blocks.12.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
127
+ "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
128
+ "transformer_blocks.12.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
129
+ "transformer_blocks.12.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
130
+ "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
131
+ "transformer_blocks.12.ff_in.bias": "diffusion_pytorch_model.safetensors",
132
+ "transformer_blocks.12.ff_in.biases": "diffusion_pytorch_model.safetensors",
133
+ "transformer_blocks.12.ff_in.scales": "diffusion_pytorch_model.safetensors",
134
+ "transformer_blocks.12.ff_in.weight": "diffusion_pytorch_model.safetensors",
135
+ "transformer_blocks.12.ff_out.bias": "diffusion_pytorch_model.safetensors",
136
+ "transformer_blocks.12.ff_out.biases": "diffusion_pytorch_model.safetensors",
137
+ "transformer_blocks.12.ff_out.scales": "diffusion_pytorch_model.safetensors",
138
+ "transformer_blocks.12.ff_out.weight": "diffusion_pytorch_model.safetensors",
139
+ "transformer_blocks.12.norm1.bias": "diffusion_pytorch_model.safetensors",
140
+ "transformer_blocks.12.norm1.weight": "diffusion_pytorch_model.safetensors",
141
+ "transformer_blocks.12.norm2.bias": "diffusion_pytorch_model.safetensors",
142
+ "transformer_blocks.12.norm2.weight": "diffusion_pytorch_model.safetensors",
143
+ "transformer_blocks.13.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
144
+ "transformer_blocks.13.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
145
+ "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
146
+ "transformer_blocks.13.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
147
+ "transformer_blocks.13.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
148
+ "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
149
+ "transformer_blocks.13.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
150
+ "transformer_blocks.13.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
151
+ "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
152
+ "transformer_blocks.13.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
153
+ "transformer_blocks.13.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
154
+ "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
155
+ "transformer_blocks.13.ff_in.bias": "diffusion_pytorch_model.safetensors",
156
+ "transformer_blocks.13.ff_in.biases": "diffusion_pytorch_model.safetensors",
157
+ "transformer_blocks.13.ff_in.scales": "diffusion_pytorch_model.safetensors",
158
+ "transformer_blocks.13.ff_in.weight": "diffusion_pytorch_model.safetensors",
159
+ "transformer_blocks.13.ff_out.bias": "diffusion_pytorch_model.safetensors",
160
+ "transformer_blocks.13.ff_out.biases": "diffusion_pytorch_model.safetensors",
161
+ "transformer_blocks.13.ff_out.scales": "diffusion_pytorch_model.safetensors",
162
+ "transformer_blocks.13.ff_out.weight": "diffusion_pytorch_model.safetensors",
163
+ "transformer_blocks.13.norm1.bias": "diffusion_pytorch_model.safetensors",
164
+ "transformer_blocks.13.norm1.weight": "diffusion_pytorch_model.safetensors",
165
+ "transformer_blocks.13.norm2.bias": "diffusion_pytorch_model.safetensors",
166
+ "transformer_blocks.13.norm2.weight": "diffusion_pytorch_model.safetensors",
167
+ "transformer_blocks.14.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
168
+ "transformer_blocks.14.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
169
+ "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
170
+ "transformer_blocks.14.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
171
+ "transformer_blocks.14.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
172
+ "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
173
+ "transformer_blocks.14.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
174
+ "transformer_blocks.14.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
175
+ "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
176
+ "transformer_blocks.14.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
177
+ "transformer_blocks.14.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
178
+ "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
179
+ "transformer_blocks.14.ff_in.bias": "diffusion_pytorch_model.safetensors",
180
+ "transformer_blocks.14.ff_in.biases": "diffusion_pytorch_model.safetensors",
181
+ "transformer_blocks.14.ff_in.scales": "diffusion_pytorch_model.safetensors",
182
+ "transformer_blocks.14.ff_in.weight": "diffusion_pytorch_model.safetensors",
183
+ "transformer_blocks.14.ff_out.bias": "diffusion_pytorch_model.safetensors",
184
+ "transformer_blocks.14.ff_out.biases": "diffusion_pytorch_model.safetensors",
185
+ "transformer_blocks.14.ff_out.scales": "diffusion_pytorch_model.safetensors",
186
+ "transformer_blocks.14.ff_out.weight": "diffusion_pytorch_model.safetensors",
187
+ "transformer_blocks.14.norm1.bias": "diffusion_pytorch_model.safetensors",
188
+ "transformer_blocks.14.norm1.weight": "diffusion_pytorch_model.safetensors",
189
+ "transformer_blocks.14.norm2.bias": "diffusion_pytorch_model.safetensors",
190
+ "transformer_blocks.14.norm2.weight": "diffusion_pytorch_model.safetensors",
191
+ "transformer_blocks.15.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
192
+ "transformer_blocks.15.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
193
+ "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
194
+ "transformer_blocks.15.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
195
+ "transformer_blocks.15.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
196
+ "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
197
+ "transformer_blocks.15.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
198
+ "transformer_blocks.15.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
199
+ "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
200
+ "transformer_blocks.15.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
201
+ "transformer_blocks.15.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
202
+ "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
203
+ "transformer_blocks.15.ff_in.bias": "diffusion_pytorch_model.safetensors",
204
+ "transformer_blocks.15.ff_in.biases": "diffusion_pytorch_model.safetensors",
205
+ "transformer_blocks.15.ff_in.scales": "diffusion_pytorch_model.safetensors",
206
+ "transformer_blocks.15.ff_in.weight": "diffusion_pytorch_model.safetensors",
207
+ "transformer_blocks.15.ff_out.bias": "diffusion_pytorch_model.safetensors",
208
+ "transformer_blocks.15.ff_out.biases": "diffusion_pytorch_model.safetensors",
209
+ "transformer_blocks.15.ff_out.scales": "diffusion_pytorch_model.safetensors",
210
+ "transformer_blocks.15.ff_out.weight": "diffusion_pytorch_model.safetensors",
211
+ "transformer_blocks.15.norm1.bias": "diffusion_pytorch_model.safetensors",
212
+ "transformer_blocks.15.norm1.weight": "diffusion_pytorch_model.safetensors",
213
+ "transformer_blocks.15.norm2.bias": "diffusion_pytorch_model.safetensors",
214
+ "transformer_blocks.15.norm2.weight": "diffusion_pytorch_model.safetensors",
215
+ "transformer_blocks.16.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
216
+ "transformer_blocks.16.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
217
+ "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
218
+ "transformer_blocks.16.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
219
+ "transformer_blocks.16.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
220
+ "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
221
+ "transformer_blocks.16.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
222
+ "transformer_blocks.16.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
223
+ "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
224
+ "transformer_blocks.16.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
225
+ "transformer_blocks.16.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
226
+ "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
227
+ "transformer_blocks.16.ff_in.bias": "diffusion_pytorch_model.safetensors",
228
+ "transformer_blocks.16.ff_in.biases": "diffusion_pytorch_model.safetensors",
229
+ "transformer_blocks.16.ff_in.scales": "diffusion_pytorch_model.safetensors",
230
+ "transformer_blocks.16.ff_in.weight": "diffusion_pytorch_model.safetensors",
231
+ "transformer_blocks.16.ff_out.bias": "diffusion_pytorch_model.safetensors",
232
+ "transformer_blocks.16.ff_out.biases": "diffusion_pytorch_model.safetensors",
233
+ "transformer_blocks.16.ff_out.scales": "diffusion_pytorch_model.safetensors",
234
+ "transformer_blocks.16.ff_out.weight": "diffusion_pytorch_model.safetensors",
235
+ "transformer_blocks.16.norm1.bias": "diffusion_pytorch_model.safetensors",
236
+ "transformer_blocks.16.norm1.weight": "diffusion_pytorch_model.safetensors",
237
+ "transformer_blocks.16.norm2.bias": "diffusion_pytorch_model.safetensors",
238
+ "transformer_blocks.16.norm2.weight": "diffusion_pytorch_model.safetensors",
239
+ "transformer_blocks.17.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
240
+ "transformer_blocks.17.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
241
+ "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
242
+ "transformer_blocks.17.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
243
+ "transformer_blocks.17.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
244
+ "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
245
+ "transformer_blocks.17.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
246
+ "transformer_blocks.17.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
247
+ "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
248
+ "transformer_blocks.17.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
249
+ "transformer_blocks.17.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
250
+ "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
251
+ "transformer_blocks.17.ff_in.bias": "diffusion_pytorch_model.safetensors",
252
+ "transformer_blocks.17.ff_in.biases": "diffusion_pytorch_model.safetensors",
253
+ "transformer_blocks.17.ff_in.scales": "diffusion_pytorch_model.safetensors",
254
+ "transformer_blocks.17.ff_in.weight": "diffusion_pytorch_model.safetensors",
255
+ "transformer_blocks.17.ff_out.bias": "diffusion_pytorch_model.safetensors",
256
+ "transformer_blocks.17.ff_out.biases": "diffusion_pytorch_model.safetensors",
257
+ "transformer_blocks.17.ff_out.scales": "diffusion_pytorch_model.safetensors",
258
+ "transformer_blocks.17.ff_out.weight": "diffusion_pytorch_model.safetensors",
259
+ "transformer_blocks.17.norm1.bias": "diffusion_pytorch_model.safetensors",
260
+ "transformer_blocks.17.norm1.weight": "diffusion_pytorch_model.safetensors",
261
+ "transformer_blocks.17.norm2.bias": "diffusion_pytorch_model.safetensors",
262
+ "transformer_blocks.17.norm2.weight": "diffusion_pytorch_model.safetensors",
263
+ "transformer_blocks.18.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
264
+ "transformer_blocks.18.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
265
+ "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
266
+ "transformer_blocks.18.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
267
+ "transformer_blocks.18.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
268
+ "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
269
+ "transformer_blocks.18.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
270
+ "transformer_blocks.18.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
271
+ "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
272
+ "transformer_blocks.18.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
273
+ "transformer_blocks.18.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
274
+ "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
275
+ "transformer_blocks.18.ff_in.bias": "diffusion_pytorch_model.safetensors",
276
+ "transformer_blocks.18.ff_in.biases": "diffusion_pytorch_model.safetensors",
277
+ "transformer_blocks.18.ff_in.scales": "diffusion_pytorch_model.safetensors",
278
+ "transformer_blocks.18.ff_in.weight": "diffusion_pytorch_model.safetensors",
279
+ "transformer_blocks.18.ff_out.bias": "diffusion_pytorch_model.safetensors",
280
+ "transformer_blocks.18.ff_out.biases": "diffusion_pytorch_model.safetensors",
281
+ "transformer_blocks.18.ff_out.scales": "diffusion_pytorch_model.safetensors",
282
+ "transformer_blocks.18.ff_out.weight": "diffusion_pytorch_model.safetensors",
283
+ "transformer_blocks.18.norm1.bias": "diffusion_pytorch_model.safetensors",
284
+ "transformer_blocks.18.norm1.weight": "diffusion_pytorch_model.safetensors",
285
+ "transformer_blocks.18.norm2.bias": "diffusion_pytorch_model.safetensors",
286
+ "transformer_blocks.18.norm2.weight": "diffusion_pytorch_model.safetensors",
287
+ "transformer_blocks.19.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
288
+ "transformer_blocks.19.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
289
+ "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
290
+ "transformer_blocks.19.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
291
+ "transformer_blocks.19.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
292
+ "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
293
+ "transformer_blocks.19.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
294
+ "transformer_blocks.19.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
295
+ "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
296
+ "transformer_blocks.19.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
297
+ "transformer_blocks.19.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
298
+ "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
299
+ "transformer_blocks.19.ff_in.bias": "diffusion_pytorch_model.safetensors",
300
+ "transformer_blocks.19.ff_in.biases": "diffusion_pytorch_model.safetensors",
301
+ "transformer_blocks.19.ff_in.scales": "diffusion_pytorch_model.safetensors",
302
+ "transformer_blocks.19.ff_in.weight": "diffusion_pytorch_model.safetensors",
303
+ "transformer_blocks.19.ff_out.bias": "diffusion_pytorch_model.safetensors",
304
+ "transformer_blocks.19.ff_out.biases": "diffusion_pytorch_model.safetensors",
305
+ "transformer_blocks.19.ff_out.scales": "diffusion_pytorch_model.safetensors",
306
+ "transformer_blocks.19.ff_out.weight": "diffusion_pytorch_model.safetensors",
307
+ "transformer_blocks.19.norm1.bias": "diffusion_pytorch_model.safetensors",
308
+ "transformer_blocks.19.norm1.weight": "diffusion_pytorch_model.safetensors",
309
+ "transformer_blocks.19.norm2.bias": "diffusion_pytorch_model.safetensors",
310
+ "transformer_blocks.19.norm2.weight": "diffusion_pytorch_model.safetensors",
311
+ "transformer_blocks.2.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
312
+ "transformer_blocks.2.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
313
+ "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
314
+ "transformer_blocks.2.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
315
+ "transformer_blocks.2.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
316
+ "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
317
+ "transformer_blocks.2.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
318
+ "transformer_blocks.2.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
319
+ "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
320
+ "transformer_blocks.2.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
321
+ "transformer_blocks.2.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
322
+ "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
323
+ "transformer_blocks.2.ff_in.bias": "diffusion_pytorch_model.safetensors",
324
+ "transformer_blocks.2.ff_in.biases": "diffusion_pytorch_model.safetensors",
325
+ "transformer_blocks.2.ff_in.scales": "diffusion_pytorch_model.safetensors",
326
+ "transformer_blocks.2.ff_in.weight": "diffusion_pytorch_model.safetensors",
327
+ "transformer_blocks.2.ff_out.bias": "diffusion_pytorch_model.safetensors",
328
+ "transformer_blocks.2.ff_out.biases": "diffusion_pytorch_model.safetensors",
329
+ "transformer_blocks.2.ff_out.scales": "diffusion_pytorch_model.safetensors",
330
+ "transformer_blocks.2.ff_out.weight": "diffusion_pytorch_model.safetensors",
331
+ "transformer_blocks.2.norm1.bias": "diffusion_pytorch_model.safetensors",
332
+ "transformer_blocks.2.norm1.weight": "diffusion_pytorch_model.safetensors",
333
+ "transformer_blocks.2.norm2.bias": "diffusion_pytorch_model.safetensors",
334
+ "transformer_blocks.2.norm2.weight": "diffusion_pytorch_model.safetensors",
335
+ "transformer_blocks.20.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
336
+ "transformer_blocks.20.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
337
+ "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
338
+ "transformer_blocks.20.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
339
+ "transformer_blocks.20.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
340
+ "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
341
+ "transformer_blocks.20.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
342
+ "transformer_blocks.20.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
343
+ "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
344
+ "transformer_blocks.20.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
345
+ "transformer_blocks.20.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
346
+ "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
347
+ "transformer_blocks.20.ff_in.bias": "diffusion_pytorch_model.safetensors",
348
+ "transformer_blocks.20.ff_in.biases": "diffusion_pytorch_model.safetensors",
349
+ "transformer_blocks.20.ff_in.scales": "diffusion_pytorch_model.safetensors",
350
+ "transformer_blocks.20.ff_in.weight": "diffusion_pytorch_model.safetensors",
351
+ "transformer_blocks.20.ff_out.bias": "diffusion_pytorch_model.safetensors",
352
+ "transformer_blocks.20.ff_out.biases": "diffusion_pytorch_model.safetensors",
353
+ "transformer_blocks.20.ff_out.scales": "diffusion_pytorch_model.safetensors",
354
+ "transformer_blocks.20.ff_out.weight": "diffusion_pytorch_model.safetensors",
355
+ "transformer_blocks.20.norm1.bias": "diffusion_pytorch_model.safetensors",
356
+ "transformer_blocks.20.norm1.weight": "diffusion_pytorch_model.safetensors",
357
+ "transformer_blocks.20.norm2.bias": "diffusion_pytorch_model.safetensors",
358
+ "transformer_blocks.20.norm2.weight": "diffusion_pytorch_model.safetensors",
359
+ "transformer_blocks.21.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
360
+ "transformer_blocks.21.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
361
+ "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
362
+ "transformer_blocks.21.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
363
+ "transformer_blocks.21.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
364
+ "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
365
+ "transformer_blocks.21.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
366
+ "transformer_blocks.21.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
367
+ "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
368
+ "transformer_blocks.21.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
369
+ "transformer_blocks.21.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
370
+ "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
371
+ "transformer_blocks.21.ff_in.bias": "diffusion_pytorch_model.safetensors",
372
+ "transformer_blocks.21.ff_in.biases": "diffusion_pytorch_model.safetensors",
373
+ "transformer_blocks.21.ff_in.scales": "diffusion_pytorch_model.safetensors",
374
+ "transformer_blocks.21.ff_in.weight": "diffusion_pytorch_model.safetensors",
375
+ "transformer_blocks.21.ff_out.bias": "diffusion_pytorch_model.safetensors",
376
+ "transformer_blocks.21.ff_out.biases": "diffusion_pytorch_model.safetensors",
377
+ "transformer_blocks.21.ff_out.scales": "diffusion_pytorch_model.safetensors",
378
+ "transformer_blocks.21.ff_out.weight": "diffusion_pytorch_model.safetensors",
379
+ "transformer_blocks.21.norm1.bias": "diffusion_pytorch_model.safetensors",
380
+ "transformer_blocks.21.norm1.weight": "diffusion_pytorch_model.safetensors",
381
+ "transformer_blocks.21.norm2.bias": "diffusion_pytorch_model.safetensors",
382
+ "transformer_blocks.21.norm2.weight": "diffusion_pytorch_model.safetensors",
383
+ "transformer_blocks.22.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
384
+ "transformer_blocks.22.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
385
+ "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
386
+ "transformer_blocks.22.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
387
+ "transformer_blocks.22.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
388
+ "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
389
+ "transformer_blocks.22.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
390
+ "transformer_blocks.22.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
391
+ "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
392
+ "transformer_blocks.22.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
393
+ "transformer_blocks.22.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
394
+ "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
395
+ "transformer_blocks.22.ff_in.bias": "diffusion_pytorch_model.safetensors",
396
+ "transformer_blocks.22.ff_in.biases": "diffusion_pytorch_model.safetensors",
397
+ "transformer_blocks.22.ff_in.scales": "diffusion_pytorch_model.safetensors",
398
+ "transformer_blocks.22.ff_in.weight": "diffusion_pytorch_model.safetensors",
399
+ "transformer_blocks.22.ff_out.bias": "diffusion_pytorch_model.safetensors",
400
+ "transformer_blocks.22.ff_out.biases": "diffusion_pytorch_model.safetensors",
401
+ "transformer_blocks.22.ff_out.scales": "diffusion_pytorch_model.safetensors",
402
+ "transformer_blocks.22.ff_out.weight": "diffusion_pytorch_model.safetensors",
403
+ "transformer_blocks.22.norm1.bias": "diffusion_pytorch_model.safetensors",
404
+ "transformer_blocks.22.norm1.weight": "diffusion_pytorch_model.safetensors",
405
+ "transformer_blocks.22.norm2.bias": "diffusion_pytorch_model.safetensors",
406
+ "transformer_blocks.22.norm2.weight": "diffusion_pytorch_model.safetensors",
407
+ "transformer_blocks.23.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
408
+ "transformer_blocks.23.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
409
+ "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
410
+ "transformer_blocks.23.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
411
+ "transformer_blocks.23.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
412
+ "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
413
+ "transformer_blocks.23.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
414
+ "transformer_blocks.23.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
415
+ "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
416
+ "transformer_blocks.23.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
417
+ "transformer_blocks.23.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
418
+ "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
419
+ "transformer_blocks.23.ff_in.bias": "diffusion_pytorch_model.safetensors",
420
+ "transformer_blocks.23.ff_in.biases": "diffusion_pytorch_model.safetensors",
421
+ "transformer_blocks.23.ff_in.scales": "diffusion_pytorch_model.safetensors",
422
+ "transformer_blocks.23.ff_in.weight": "diffusion_pytorch_model.safetensors",
423
+ "transformer_blocks.23.ff_out.bias": "diffusion_pytorch_model.safetensors",
424
+ "transformer_blocks.23.ff_out.biases": "diffusion_pytorch_model.safetensors",
425
+ "transformer_blocks.23.ff_out.scales": "diffusion_pytorch_model.safetensors",
426
+ "transformer_blocks.23.ff_out.weight": "diffusion_pytorch_model.safetensors",
427
+ "transformer_blocks.23.norm1.bias": "diffusion_pytorch_model.safetensors",
428
+ "transformer_blocks.23.norm1.weight": "diffusion_pytorch_model.safetensors",
429
+ "transformer_blocks.23.norm2.bias": "diffusion_pytorch_model.safetensors",
430
+ "transformer_blocks.23.norm2.weight": "diffusion_pytorch_model.safetensors",
431
+ "transformer_blocks.24.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
432
+ "transformer_blocks.24.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
433
+ "transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
434
+ "transformer_blocks.24.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
435
+ "transformer_blocks.24.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
436
+ "transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
437
+ "transformer_blocks.24.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
438
+ "transformer_blocks.24.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
439
+ "transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
440
+ "transformer_blocks.24.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
441
+ "transformer_blocks.24.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
442
+ "transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
443
+ "transformer_blocks.24.ff_in.bias": "diffusion_pytorch_model.safetensors",
444
+ "transformer_blocks.24.ff_in.biases": "diffusion_pytorch_model.safetensors",
445
+ "transformer_blocks.24.ff_in.scales": "diffusion_pytorch_model.safetensors",
446
+ "transformer_blocks.24.ff_in.weight": "diffusion_pytorch_model.safetensors",
447
+ "transformer_blocks.24.ff_out.bias": "diffusion_pytorch_model.safetensors",
448
+ "transformer_blocks.24.ff_out.biases": "diffusion_pytorch_model.safetensors",
449
+ "transformer_blocks.24.ff_out.scales": "diffusion_pytorch_model.safetensors",
450
+ "transformer_blocks.24.ff_out.weight": "diffusion_pytorch_model.safetensors",
451
+ "transformer_blocks.24.norm1.bias": "diffusion_pytorch_model.safetensors",
452
+ "transformer_blocks.24.norm1.weight": "diffusion_pytorch_model.safetensors",
453
+ "transformer_blocks.24.norm2.bias": "diffusion_pytorch_model.safetensors",
454
+ "transformer_blocks.24.norm2.weight": "diffusion_pytorch_model.safetensors",
455
+ "transformer_blocks.25.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
456
+ "transformer_blocks.25.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
457
+ "transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
458
+ "transformer_blocks.25.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
459
+ "transformer_blocks.25.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
460
+ "transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
461
+ "transformer_blocks.25.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
462
+ "transformer_blocks.25.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
463
+ "transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
464
+ "transformer_blocks.25.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
465
+ "transformer_blocks.25.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
466
+ "transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
467
+ "transformer_blocks.25.ff_in.bias": "diffusion_pytorch_model.safetensors",
468
+ "transformer_blocks.25.ff_in.biases": "diffusion_pytorch_model.safetensors",
469
+ "transformer_blocks.25.ff_in.scales": "diffusion_pytorch_model.safetensors",
470
+ "transformer_blocks.25.ff_in.weight": "diffusion_pytorch_model.safetensors",
471
+ "transformer_blocks.25.ff_out.bias": "diffusion_pytorch_model.safetensors",
472
+ "transformer_blocks.25.ff_out.biases": "diffusion_pytorch_model.safetensors",
473
+ "transformer_blocks.25.ff_out.scales": "diffusion_pytorch_model.safetensors",
474
+ "transformer_blocks.25.ff_out.weight": "diffusion_pytorch_model.safetensors",
475
+ "transformer_blocks.25.norm1.bias": "diffusion_pytorch_model.safetensors",
476
+ "transformer_blocks.25.norm1.weight": "diffusion_pytorch_model.safetensors",
477
+ "transformer_blocks.25.norm2.bias": "diffusion_pytorch_model.safetensors",
478
+ "transformer_blocks.25.norm2.weight": "diffusion_pytorch_model.safetensors",
479
+ "transformer_blocks.26.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
480
+ "transformer_blocks.26.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
481
+ "transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
482
+ "transformer_blocks.26.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
483
+ "transformer_blocks.26.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
484
+ "transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
485
+ "transformer_blocks.26.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
486
+ "transformer_blocks.26.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
487
+ "transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
488
+ "transformer_blocks.26.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
489
+ "transformer_blocks.26.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
490
+ "transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
491
+ "transformer_blocks.26.ff_in.bias": "diffusion_pytorch_model.safetensors",
492
+ "transformer_blocks.26.ff_in.biases": "diffusion_pytorch_model.safetensors",
493
+ "transformer_blocks.26.ff_in.scales": "diffusion_pytorch_model.safetensors",
494
+ "transformer_blocks.26.ff_in.weight": "diffusion_pytorch_model.safetensors",
495
+ "transformer_blocks.26.ff_out.bias": "diffusion_pytorch_model.safetensors",
496
+ "transformer_blocks.26.ff_out.biases": "diffusion_pytorch_model.safetensors",
497
+ "transformer_blocks.26.ff_out.scales": "diffusion_pytorch_model.safetensors",
498
+ "transformer_blocks.26.ff_out.weight": "diffusion_pytorch_model.safetensors",
499
+ "transformer_blocks.26.norm1.bias": "diffusion_pytorch_model.safetensors",
500
+ "transformer_blocks.26.norm1.weight": "diffusion_pytorch_model.safetensors",
501
+ "transformer_blocks.26.norm2.bias": "diffusion_pytorch_model.safetensors",
502
+ "transformer_blocks.26.norm2.weight": "diffusion_pytorch_model.safetensors",
503
+ "transformer_blocks.27.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
504
+ "transformer_blocks.27.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
505
+ "transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
506
+ "transformer_blocks.27.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
507
+ "transformer_blocks.27.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
508
+ "transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
509
+ "transformer_blocks.27.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
510
+ "transformer_blocks.27.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
511
+ "transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
512
+ "transformer_blocks.27.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
513
+ "transformer_blocks.27.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
514
+ "transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
515
+ "transformer_blocks.27.ff_in.bias": "diffusion_pytorch_model.safetensors",
516
+ "transformer_blocks.27.ff_in.biases": "diffusion_pytorch_model.safetensors",
517
+ "transformer_blocks.27.ff_in.scales": "diffusion_pytorch_model.safetensors",
518
+ "transformer_blocks.27.ff_in.weight": "diffusion_pytorch_model.safetensors",
519
+ "transformer_blocks.27.ff_out.bias": "diffusion_pytorch_model.safetensors",
520
+ "transformer_blocks.27.ff_out.biases": "diffusion_pytorch_model.safetensors",
521
+ "transformer_blocks.27.ff_out.scales": "diffusion_pytorch_model.safetensors",
522
+ "transformer_blocks.27.ff_out.weight": "diffusion_pytorch_model.safetensors",
523
+ "transformer_blocks.27.norm1.bias": "diffusion_pytorch_model.safetensors",
524
+ "transformer_blocks.27.norm1.weight": "diffusion_pytorch_model.safetensors",
525
+ "transformer_blocks.27.norm2.bias": "diffusion_pytorch_model.safetensors",
526
+ "transformer_blocks.27.norm2.weight": "diffusion_pytorch_model.safetensors",
527
+ "transformer_blocks.28.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
528
+ "transformer_blocks.28.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
529
+ "transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
530
+ "transformer_blocks.28.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
531
+ "transformer_blocks.28.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
532
+ "transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
533
+ "transformer_blocks.28.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
534
+ "transformer_blocks.28.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
535
+ "transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
536
+ "transformer_blocks.28.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
537
+ "transformer_blocks.28.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
538
+ "transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
539
+ "transformer_blocks.28.ff_in.bias": "diffusion_pytorch_model.safetensors",
540
+ "transformer_blocks.28.ff_in.biases": "diffusion_pytorch_model.safetensors",
541
+ "transformer_blocks.28.ff_in.scales": "diffusion_pytorch_model.safetensors",
542
+ "transformer_blocks.28.ff_in.weight": "diffusion_pytorch_model.safetensors",
543
+ "transformer_blocks.28.ff_out.bias": "diffusion_pytorch_model.safetensors",
544
+ "transformer_blocks.28.ff_out.biases": "diffusion_pytorch_model.safetensors",
545
+ "transformer_blocks.28.ff_out.scales": "diffusion_pytorch_model.safetensors",
546
+ "transformer_blocks.28.ff_out.weight": "diffusion_pytorch_model.safetensors",
547
+ "transformer_blocks.28.norm1.bias": "diffusion_pytorch_model.safetensors",
548
+ "transformer_blocks.28.norm1.weight": "diffusion_pytorch_model.safetensors",
549
+ "transformer_blocks.28.norm2.bias": "diffusion_pytorch_model.safetensors",
550
+ "transformer_blocks.28.norm2.weight": "diffusion_pytorch_model.safetensors",
551
+ "transformer_blocks.29.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
552
+ "transformer_blocks.29.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
553
+ "transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
554
+ "transformer_blocks.29.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
555
+ "transformer_blocks.29.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
556
+ "transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
557
+ "transformer_blocks.29.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
558
+ "transformer_blocks.29.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
559
+ "transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
560
+ "transformer_blocks.29.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
561
+ "transformer_blocks.29.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
562
+ "transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
563
+ "transformer_blocks.29.ff_in.bias": "diffusion_pytorch_model.safetensors",
564
+ "transformer_blocks.29.ff_in.biases": "diffusion_pytorch_model.safetensors",
565
+ "transformer_blocks.29.ff_in.scales": "diffusion_pytorch_model.safetensors",
566
+ "transformer_blocks.29.ff_in.weight": "diffusion_pytorch_model.safetensors",
567
+ "transformer_blocks.29.ff_out.bias": "diffusion_pytorch_model.safetensors",
568
+ "transformer_blocks.29.ff_out.biases": "diffusion_pytorch_model.safetensors",
569
+ "transformer_blocks.29.ff_out.scales": "diffusion_pytorch_model.safetensors",
570
+ "transformer_blocks.29.ff_out.weight": "diffusion_pytorch_model.safetensors",
571
+ "transformer_blocks.29.norm1.bias": "diffusion_pytorch_model.safetensors",
572
+ "transformer_blocks.29.norm1.weight": "diffusion_pytorch_model.safetensors",
573
+ "transformer_blocks.29.norm2.bias": "diffusion_pytorch_model.safetensors",
574
+ "transformer_blocks.29.norm2.weight": "diffusion_pytorch_model.safetensors",
575
+ "transformer_blocks.3.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
576
+ "transformer_blocks.3.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
577
+ "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
578
+ "transformer_blocks.3.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
579
+ "transformer_blocks.3.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
580
+ "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
581
+ "transformer_blocks.3.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
582
+ "transformer_blocks.3.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
583
+ "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
584
+ "transformer_blocks.3.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
585
+ "transformer_blocks.3.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
586
+ "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
587
+ "transformer_blocks.3.ff_in.bias": "diffusion_pytorch_model.safetensors",
588
+ "transformer_blocks.3.ff_in.biases": "diffusion_pytorch_model.safetensors",
589
+ "transformer_blocks.3.ff_in.scales": "diffusion_pytorch_model.safetensors",
590
+ "transformer_blocks.3.ff_in.weight": "diffusion_pytorch_model.safetensors",
591
+ "transformer_blocks.3.ff_out.bias": "diffusion_pytorch_model.safetensors",
592
+ "transformer_blocks.3.ff_out.biases": "diffusion_pytorch_model.safetensors",
593
+ "transformer_blocks.3.ff_out.scales": "diffusion_pytorch_model.safetensors",
594
+ "transformer_blocks.3.ff_out.weight": "diffusion_pytorch_model.safetensors",
595
+ "transformer_blocks.3.norm1.bias": "diffusion_pytorch_model.safetensors",
596
+ "transformer_blocks.3.norm1.weight": "diffusion_pytorch_model.safetensors",
597
+ "transformer_blocks.3.norm2.bias": "diffusion_pytorch_model.safetensors",
598
+ "transformer_blocks.3.norm2.weight": "diffusion_pytorch_model.safetensors",
599
+ "transformer_blocks.30.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
600
+ "transformer_blocks.30.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
601
+ "transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
602
+ "transformer_blocks.30.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
603
+ "transformer_blocks.30.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
604
+ "transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
605
+ "transformer_blocks.30.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
606
+ "transformer_blocks.30.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
607
+ "transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
608
+ "transformer_blocks.30.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
609
+ "transformer_blocks.30.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
610
+ "transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
611
+ "transformer_blocks.30.ff_in.bias": "diffusion_pytorch_model.safetensors",
612
+ "transformer_blocks.30.ff_in.biases": "diffusion_pytorch_model.safetensors",
613
+ "transformer_blocks.30.ff_in.scales": "diffusion_pytorch_model.safetensors",
614
+ "transformer_blocks.30.ff_in.weight": "diffusion_pytorch_model.safetensors",
615
+ "transformer_blocks.30.ff_out.bias": "diffusion_pytorch_model.safetensors",
616
+ "transformer_blocks.30.ff_out.biases": "diffusion_pytorch_model.safetensors",
617
+ "transformer_blocks.30.ff_out.scales": "diffusion_pytorch_model.safetensors",
618
+ "transformer_blocks.30.ff_out.weight": "diffusion_pytorch_model.safetensors",
619
+ "transformer_blocks.30.norm1.bias": "diffusion_pytorch_model.safetensors",
620
+ "transformer_blocks.30.norm1.weight": "diffusion_pytorch_model.safetensors",
621
+ "transformer_blocks.30.norm2.bias": "diffusion_pytorch_model.safetensors",
622
+ "transformer_blocks.30.norm2.weight": "diffusion_pytorch_model.safetensors",
623
+ "transformer_blocks.31.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
624
+ "transformer_blocks.31.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
625
+ "transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
626
+ "transformer_blocks.31.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
627
+ "transformer_blocks.31.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
628
+ "transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
629
+ "transformer_blocks.31.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
630
+ "transformer_blocks.31.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
631
+ "transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
632
+ "transformer_blocks.31.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
633
+ "transformer_blocks.31.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
634
+ "transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
635
+ "transformer_blocks.31.ff_in.bias": "diffusion_pytorch_model.safetensors",
636
+ "transformer_blocks.31.ff_in.biases": "diffusion_pytorch_model.safetensors",
637
+ "transformer_blocks.31.ff_in.scales": "diffusion_pytorch_model.safetensors",
638
+ "transformer_blocks.31.ff_in.weight": "diffusion_pytorch_model.safetensors",
639
+ "transformer_blocks.31.ff_out.bias": "diffusion_pytorch_model.safetensors",
640
+ "transformer_blocks.31.ff_out.biases": "diffusion_pytorch_model.safetensors",
641
+ "transformer_blocks.31.ff_out.scales": "diffusion_pytorch_model.safetensors",
642
+ "transformer_blocks.31.ff_out.weight": "diffusion_pytorch_model.safetensors",
643
+ "transformer_blocks.31.norm1.bias": "diffusion_pytorch_model.safetensors",
644
+ "transformer_blocks.31.norm1.weight": "diffusion_pytorch_model.safetensors",
645
+ "transformer_blocks.31.norm2.bias": "diffusion_pytorch_model.safetensors",
646
+ "transformer_blocks.31.norm2.weight": "diffusion_pytorch_model.safetensors",
647
+ "transformer_blocks.32.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
648
+ "transformer_blocks.32.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
649
+ "transformer_blocks.32.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
650
+ "transformer_blocks.32.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
651
+ "transformer_blocks.32.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
652
+ "transformer_blocks.32.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
653
+ "transformer_blocks.32.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
654
+ "transformer_blocks.32.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
655
+ "transformer_blocks.32.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
656
+ "transformer_blocks.32.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
657
+ "transformer_blocks.32.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
658
+ "transformer_blocks.32.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
659
+ "transformer_blocks.32.ff_in.bias": "diffusion_pytorch_model.safetensors",
660
+ "transformer_blocks.32.ff_in.biases": "diffusion_pytorch_model.safetensors",
661
+ "transformer_blocks.32.ff_in.scales": "diffusion_pytorch_model.safetensors",
662
+ "transformer_blocks.32.ff_in.weight": "diffusion_pytorch_model.safetensors",
663
+ "transformer_blocks.32.ff_out.bias": "diffusion_pytorch_model.safetensors",
664
+ "transformer_blocks.32.ff_out.biases": "diffusion_pytorch_model.safetensors",
665
+ "transformer_blocks.32.ff_out.scales": "diffusion_pytorch_model.safetensors",
666
+ "transformer_blocks.32.ff_out.weight": "diffusion_pytorch_model.safetensors",
667
+ "transformer_blocks.32.norm1.bias": "diffusion_pytorch_model.safetensors",
668
+ "transformer_blocks.32.norm1.weight": "diffusion_pytorch_model.safetensors",
669
+ "transformer_blocks.32.norm2.bias": "diffusion_pytorch_model.safetensors",
670
+ "transformer_blocks.32.norm2.weight": "diffusion_pytorch_model.safetensors",
671
+ "transformer_blocks.33.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
672
+ "transformer_blocks.33.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
673
+ "transformer_blocks.33.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
674
+ "transformer_blocks.33.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
675
+ "transformer_blocks.33.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
676
+ "transformer_blocks.33.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
677
+ "transformer_blocks.33.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
678
+ "transformer_blocks.33.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
679
+ "transformer_blocks.33.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
680
+ "transformer_blocks.33.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
681
+ "transformer_blocks.33.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
682
+ "transformer_blocks.33.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
683
+ "transformer_blocks.33.ff_in.bias": "diffusion_pytorch_model.safetensors",
684
+ "transformer_blocks.33.ff_in.biases": "diffusion_pytorch_model.safetensors",
685
+ "transformer_blocks.33.ff_in.scales": "diffusion_pytorch_model.safetensors",
686
+ "transformer_blocks.33.ff_in.weight": "diffusion_pytorch_model.safetensors",
687
+ "transformer_blocks.33.ff_out.bias": "diffusion_pytorch_model.safetensors",
688
+ "transformer_blocks.33.ff_out.biases": "diffusion_pytorch_model.safetensors",
689
+ "transformer_blocks.33.ff_out.scales": "diffusion_pytorch_model.safetensors",
690
+ "transformer_blocks.33.ff_out.weight": "diffusion_pytorch_model.safetensors",
691
+ "transformer_blocks.33.norm1.bias": "diffusion_pytorch_model.safetensors",
692
+ "transformer_blocks.33.norm1.weight": "diffusion_pytorch_model.safetensors",
693
+ "transformer_blocks.33.norm2.bias": "diffusion_pytorch_model.safetensors",
694
+ "transformer_blocks.33.norm2.weight": "diffusion_pytorch_model.safetensors",
695
+ "transformer_blocks.34.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
696
+ "transformer_blocks.34.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
697
+ "transformer_blocks.34.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
698
+ "transformer_blocks.34.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
699
+ "transformer_blocks.34.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
700
+ "transformer_blocks.34.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
701
+ "transformer_blocks.34.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
702
+ "transformer_blocks.34.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
703
+ "transformer_blocks.34.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
704
+ "transformer_blocks.34.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
705
+ "transformer_blocks.34.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
706
+ "transformer_blocks.34.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
707
+ "transformer_blocks.34.ff_in.bias": "diffusion_pytorch_model.safetensors",
708
+ "transformer_blocks.34.ff_in.biases": "diffusion_pytorch_model.safetensors",
709
+ "transformer_blocks.34.ff_in.scales": "diffusion_pytorch_model.safetensors",
710
+ "transformer_blocks.34.ff_in.weight": "diffusion_pytorch_model.safetensors",
711
+ "transformer_blocks.34.ff_out.bias": "diffusion_pytorch_model.safetensors",
712
+ "transformer_blocks.34.ff_out.biases": "diffusion_pytorch_model.safetensors",
713
+ "transformer_blocks.34.ff_out.scales": "diffusion_pytorch_model.safetensors",
714
+ "transformer_blocks.34.ff_out.weight": "diffusion_pytorch_model.safetensors",
715
+ "transformer_blocks.34.norm1.bias": "diffusion_pytorch_model.safetensors",
716
+ "transformer_blocks.34.norm1.weight": "diffusion_pytorch_model.safetensors",
717
+ "transformer_blocks.34.norm2.bias": "diffusion_pytorch_model.safetensors",
718
+ "transformer_blocks.34.norm2.weight": "diffusion_pytorch_model.safetensors",
719
+ "transformer_blocks.35.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
720
+ "transformer_blocks.35.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
721
+ "transformer_blocks.35.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
722
+ "transformer_blocks.35.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
723
+ "transformer_blocks.35.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
724
+ "transformer_blocks.35.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
725
+ "transformer_blocks.35.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
726
+ "transformer_blocks.35.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
727
+ "transformer_blocks.35.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
728
+ "transformer_blocks.35.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
729
+ "transformer_blocks.35.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
730
+ "transformer_blocks.35.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
731
+ "transformer_blocks.35.ff_in.bias": "diffusion_pytorch_model.safetensors",
732
+ "transformer_blocks.35.ff_in.biases": "diffusion_pytorch_model.safetensors",
733
+ "transformer_blocks.35.ff_in.scales": "diffusion_pytorch_model.safetensors",
734
+ "transformer_blocks.35.ff_in.weight": "diffusion_pytorch_model.safetensors",
735
+ "transformer_blocks.35.ff_out.bias": "diffusion_pytorch_model.safetensors",
736
+ "transformer_blocks.35.ff_out.biases": "diffusion_pytorch_model.safetensors",
737
+ "transformer_blocks.35.ff_out.scales": "diffusion_pytorch_model.safetensors",
738
+ "transformer_blocks.35.ff_out.weight": "diffusion_pytorch_model.safetensors",
739
+ "transformer_blocks.35.norm1.bias": "diffusion_pytorch_model.safetensors",
740
+ "transformer_blocks.35.norm1.weight": "diffusion_pytorch_model.safetensors",
741
+ "transformer_blocks.35.norm2.bias": "diffusion_pytorch_model.safetensors",
742
+ "transformer_blocks.35.norm2.weight": "diffusion_pytorch_model.safetensors",
743
+ "transformer_blocks.4.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
744
+ "transformer_blocks.4.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
745
+ "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
746
+ "transformer_blocks.4.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
747
+ "transformer_blocks.4.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
748
+ "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
749
+ "transformer_blocks.4.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
750
+ "transformer_blocks.4.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
751
+ "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
752
+ "transformer_blocks.4.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
753
+ "transformer_blocks.4.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
754
+ "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
755
+ "transformer_blocks.4.ff_in.bias": "diffusion_pytorch_model.safetensors",
756
+ "transformer_blocks.4.ff_in.biases": "diffusion_pytorch_model.safetensors",
757
+ "transformer_blocks.4.ff_in.scales": "diffusion_pytorch_model.safetensors",
758
+ "transformer_blocks.4.ff_in.weight": "diffusion_pytorch_model.safetensors",
759
+ "transformer_blocks.4.ff_out.bias": "diffusion_pytorch_model.safetensors",
760
+ "transformer_blocks.4.ff_out.biases": "diffusion_pytorch_model.safetensors",
761
+ "transformer_blocks.4.ff_out.scales": "diffusion_pytorch_model.safetensors",
762
+ "transformer_blocks.4.ff_out.weight": "diffusion_pytorch_model.safetensors",
763
+ "transformer_blocks.4.norm1.bias": "diffusion_pytorch_model.safetensors",
764
+ "transformer_blocks.4.norm1.weight": "diffusion_pytorch_model.safetensors",
765
+ "transformer_blocks.4.norm2.bias": "diffusion_pytorch_model.safetensors",
766
+ "transformer_blocks.4.norm2.weight": "diffusion_pytorch_model.safetensors",
767
+ "transformer_blocks.5.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
768
+ "transformer_blocks.5.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
769
+ "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
770
+ "transformer_blocks.5.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
771
+ "transformer_blocks.5.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
772
+ "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
773
+ "transformer_blocks.5.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
774
+ "transformer_blocks.5.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
775
+ "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
776
+ "transformer_blocks.5.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
777
+ "transformer_blocks.5.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
778
+ "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
779
+ "transformer_blocks.5.ff_in.bias": "diffusion_pytorch_model.safetensors",
780
+ "transformer_blocks.5.ff_in.biases": "diffusion_pytorch_model.safetensors",
781
+ "transformer_blocks.5.ff_in.scales": "diffusion_pytorch_model.safetensors",
782
+ "transformer_blocks.5.ff_in.weight": "diffusion_pytorch_model.safetensors",
783
+ "transformer_blocks.5.ff_out.bias": "diffusion_pytorch_model.safetensors",
784
+ "transformer_blocks.5.ff_out.biases": "diffusion_pytorch_model.safetensors",
785
+ "transformer_blocks.5.ff_out.scales": "diffusion_pytorch_model.safetensors",
786
+ "transformer_blocks.5.ff_out.weight": "diffusion_pytorch_model.safetensors",
787
+ "transformer_blocks.5.norm1.bias": "diffusion_pytorch_model.safetensors",
788
+ "transformer_blocks.5.norm1.weight": "diffusion_pytorch_model.safetensors",
789
+ "transformer_blocks.5.norm2.bias": "diffusion_pytorch_model.safetensors",
790
+ "transformer_blocks.5.norm2.weight": "diffusion_pytorch_model.safetensors",
791
+ "transformer_blocks.6.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
792
+ "transformer_blocks.6.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
793
+ "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
794
+ "transformer_blocks.6.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
795
+ "transformer_blocks.6.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
796
+ "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
797
+ "transformer_blocks.6.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
798
+ "transformer_blocks.6.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
799
+ "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
800
+ "transformer_blocks.6.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
801
+ "transformer_blocks.6.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
802
+ "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
803
+ "transformer_blocks.6.ff_in.bias": "diffusion_pytorch_model.safetensors",
804
+ "transformer_blocks.6.ff_in.biases": "diffusion_pytorch_model.safetensors",
805
+ "transformer_blocks.6.ff_in.scales": "diffusion_pytorch_model.safetensors",
806
+ "transformer_blocks.6.ff_in.weight": "diffusion_pytorch_model.safetensors",
807
+ "transformer_blocks.6.ff_out.bias": "diffusion_pytorch_model.safetensors",
808
+ "transformer_blocks.6.ff_out.biases": "diffusion_pytorch_model.safetensors",
809
+ "transformer_blocks.6.ff_out.scales": "diffusion_pytorch_model.safetensors",
810
+ "transformer_blocks.6.ff_out.weight": "diffusion_pytorch_model.safetensors",
811
+ "transformer_blocks.6.norm1.bias": "diffusion_pytorch_model.safetensors",
812
+ "transformer_blocks.6.norm1.weight": "diffusion_pytorch_model.safetensors",
813
+ "transformer_blocks.6.norm2.bias": "diffusion_pytorch_model.safetensors",
814
+ "transformer_blocks.6.norm2.weight": "diffusion_pytorch_model.safetensors",
815
+ "transformer_blocks.7.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
816
+ "transformer_blocks.7.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
817
+ "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
818
+ "transformer_blocks.7.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
819
+ "transformer_blocks.7.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
820
+ "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
821
+ "transformer_blocks.7.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
822
+ "transformer_blocks.7.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
823
+ "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
824
+ "transformer_blocks.7.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
825
+ "transformer_blocks.7.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
826
+ "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
827
+ "transformer_blocks.7.ff_in.bias": "diffusion_pytorch_model.safetensors",
828
+ "transformer_blocks.7.ff_in.biases": "diffusion_pytorch_model.safetensors",
829
+ "transformer_blocks.7.ff_in.scales": "diffusion_pytorch_model.safetensors",
830
+ "transformer_blocks.7.ff_in.weight": "diffusion_pytorch_model.safetensors",
831
+ "transformer_blocks.7.ff_out.bias": "diffusion_pytorch_model.safetensors",
832
+ "transformer_blocks.7.ff_out.biases": "diffusion_pytorch_model.safetensors",
833
+ "transformer_blocks.7.ff_out.scales": "diffusion_pytorch_model.safetensors",
834
+ "transformer_blocks.7.ff_out.weight": "diffusion_pytorch_model.safetensors",
835
+ "transformer_blocks.7.norm1.bias": "diffusion_pytorch_model.safetensors",
836
+ "transformer_blocks.7.norm1.weight": "diffusion_pytorch_model.safetensors",
837
+ "transformer_blocks.7.norm2.bias": "diffusion_pytorch_model.safetensors",
838
+ "transformer_blocks.7.norm2.weight": "diffusion_pytorch_model.safetensors",
839
+ "transformer_blocks.8.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
840
+ "transformer_blocks.8.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
841
+ "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
842
+ "transformer_blocks.8.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
843
+ "transformer_blocks.8.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
844
+ "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
845
+ "transformer_blocks.8.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
846
+ "transformer_blocks.8.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
847
+ "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
848
+ "transformer_blocks.8.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
849
+ "transformer_blocks.8.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
850
+ "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
851
+ "transformer_blocks.8.ff_in.bias": "diffusion_pytorch_model.safetensors",
852
+ "transformer_blocks.8.ff_in.biases": "diffusion_pytorch_model.safetensors",
853
+ "transformer_blocks.8.ff_in.scales": "diffusion_pytorch_model.safetensors",
854
+ "transformer_blocks.8.ff_in.weight": "diffusion_pytorch_model.safetensors",
855
+ "transformer_blocks.8.ff_out.bias": "diffusion_pytorch_model.safetensors",
856
+ "transformer_blocks.8.ff_out.biases": "diffusion_pytorch_model.safetensors",
857
+ "transformer_blocks.8.ff_out.scales": "diffusion_pytorch_model.safetensors",
858
+ "transformer_blocks.8.ff_out.weight": "diffusion_pytorch_model.safetensors",
859
+ "transformer_blocks.8.norm1.bias": "diffusion_pytorch_model.safetensors",
860
+ "transformer_blocks.8.norm1.weight": "diffusion_pytorch_model.safetensors",
861
+ "transformer_blocks.8.norm2.bias": "diffusion_pytorch_model.safetensors",
862
+ "transformer_blocks.8.norm2.weight": "diffusion_pytorch_model.safetensors",
863
+ "transformer_blocks.9.attn.to_k.biases": "diffusion_pytorch_model.safetensors",
864
+ "transformer_blocks.9.attn.to_k.scales": "diffusion_pytorch_model.safetensors",
865
+ "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model.safetensors",
866
+ "transformer_blocks.9.attn.to_out.0.biases": "diffusion_pytorch_model.safetensors",
867
+ "transformer_blocks.9.attn.to_out.0.scales": "diffusion_pytorch_model.safetensors",
868
+ "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model.safetensors",
869
+ "transformer_blocks.9.attn.to_q.biases": "diffusion_pytorch_model.safetensors",
870
+ "transformer_blocks.9.attn.to_q.scales": "diffusion_pytorch_model.safetensors",
871
+ "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model.safetensors",
872
+ "transformer_blocks.9.attn.to_v.biases": "diffusion_pytorch_model.safetensors",
873
+ "transformer_blocks.9.attn.to_v.scales": "diffusion_pytorch_model.safetensors",
874
+ "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model.safetensors",
875
+ "transformer_blocks.9.ff_in.bias": "diffusion_pytorch_model.safetensors",
876
+ "transformer_blocks.9.ff_in.biases": "diffusion_pytorch_model.safetensors",
877
+ "transformer_blocks.9.ff_in.scales": "diffusion_pytorch_model.safetensors",
878
+ "transformer_blocks.9.ff_in.weight": "diffusion_pytorch_model.safetensors",
879
+ "transformer_blocks.9.ff_out.bias": "diffusion_pytorch_model.safetensors",
880
+ "transformer_blocks.9.ff_out.biases": "diffusion_pytorch_model.safetensors",
881
+ "transformer_blocks.9.ff_out.scales": "diffusion_pytorch_model.safetensors",
882
+ "transformer_blocks.9.ff_out.weight": "diffusion_pytorch_model.safetensors",
883
+ "transformer_blocks.9.norm1.bias": "diffusion_pytorch_model.safetensors",
884
+ "transformer_blocks.9.norm1.weight": "diffusion_pytorch_model.safetensors",
885
+ "transformer_blocks.9.norm2.bias": "diffusion_pytorch_model.safetensors",
886
+ "transformer_blocks.9.norm2.weight": "diffusion_pytorch_model.safetensors"
887
+ }
888
+ }
vocoder/config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "MiniMaxMusic3Vocoder",
3
+ "_diffusers_version": "0.40.0.dev0",
4
+ "decoder_hidden_dim": 1536,
5
+ "decoder_input_dim": 1024,
6
+ "latent_channels": 128,
7
+ "sampling_rate": 44100,
8
+ "upsampling_ratios": [
9
+ 8,
10
+ 8,
11
+ 4,
12
+ 2
13
+ ]
14
+ }