Hugging Face's logo

Intel
/
Ovis-Image-7B-int4-AutoRound

Text-to-Image
Diffusers
Safetensors
OvisImagePipeline
Text-to-Image
Model card Files
xet
 Community
lianglv commited on
Commit
8ac85fc
·
verified ·
1 Parent(s): f701f13

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. model_index.json +25 -0
  3. scheduler/scheduler_config.json +18 -0
  4. text_encoder/config.json +64 -0
  5. text_encoder/model.safetensors +3 -0
  6. tokenizer/chat_template.jinja +10 -0
  7. tokenizer/tokenizer.json +3 -0
  8. tokenizer/tokenizer_config.json +15 -0
  9. transformer/config.json +30 -0
  10. transformer/model-00001-of-00004.safetensors +3 -0
  11. transformer/model-00002-of-00004.safetensors +3 -0
  12. transformer/model-00003-of-00004.safetensors +3 -0
  13. transformer/model-00004-of-00004.safetensors +3 -0
  14. transformer/model.safetensors.index.json +1085 -0
  15. transformer/quantization_config.json +12 -0
  16. vae/config.json +38 -0
  17. vae/diffusion_pytorch_model.safetensors +3 -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
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "OvisImagePipeline",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "/mnt/disk4/lvl/Ovis-Image-7B",
5
+ "scheduler": [
6
+ "diffusers",
7
+ "FlowMatchEulerDiscreteScheduler"
8
+ ],
9
+ "text_encoder": [
10
+ "transformers",
11
+ "Qwen3Model"
12
+ ],
13
+ "tokenizer": [
14
+ "transformers",
15
+ "Qwen2Tokenizer"
16
+ ],
17
+ "transformer": [
18
+ "diffusers",
19
+ "OvisImageTransformer2DModel"
20
+ ],
21
+ "vae": [
22
+ "diffusers",
23
+ "AutoencoderKL"
24
+ ]
25
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 4096,
8
+ "max_shift": 1.15,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 3.0,
11
+ "shift_terminal": null,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen3Model"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151643,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6144,
16
+ "layer_types": [
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
+ ],
46
+ "max_position_embeddings": 40960,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "num_attention_heads": 16,
50
+ "num_hidden_layers": 28,
51
+ "num_key_value_heads": 8,
52
+ "pad_token_id": null,
53
+ "rms_norm_eps": 1e-06,
54
+ "rope_parameters": {
55
+ "rope_theta": 1000000,
56
+ "rope_type": "default"
57
+ },
58
+ "sliding_window": null,
59
+ "tie_word_embeddings": true,
60
+ "transformers_version": "5.7.0",
61
+ "use_cache": true,
62
+ "use_sliding_window": false,
63
+ "vocab_size": 151936
64
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd61165ab387530f73813cf5e1ac18819c535ea8b9a1111a7d87cc79543f5cd9
3
+ size 3441183752
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- for message in messages %}{{- '<|im_start|>' + message.role + '
2
+ '}}{%- if message.role == 'system' or message.role == 'user' %}{%- if message.content is string %}{{- message.content | replace('<image>', '') | replace('<video>', '') }}{%- else %}{%- for item in message.content %}{%- if item.type == 'text' and 'text' in item %}{{- item.text | replace('<image>', '') | replace('<video>', '') }}{%- elif item.type == 'image' %}{{- '<image>'}}{%- elif item.type == 'video' %}{{- '<video>'}}{%- else %}{{- raise_exception('Invalid content type. Supported types for system and user are text, image, video.')}}{%- endif %}{%- if not loop.last %}{{- '
3
+ '}}{%- endif %}{%- endfor %}{%- endif %}{%- elif message.role == 'assistant' %}{%- set content = '' %}{%- if message.content is string %}{%- set content = message.content | replace('<image>', '') | replace('<video>', '') %}{%- else %}{%- for item in message.content %}{%- if item.type == 'text' and 'text' in item %}{%- set content = content ~ (item.text | replace('<image>', '') | replace('<video>', '')) %}{%- else %}{{- raise_exception('Invalid content type. Supported type for assistant is text.')}}{%- endif %}{%- endfor %}{%- endif %}{%- set content = content.split('</think>')[-1].lstrip('
4
+ ') %}{{- content }}{%- else %}{{- raise_exception('Invalid role. Supported roles are system, user, assistant.')}}{%- endif %}{{- '<|im_end|>
5
+ '}}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant
6
+ ' }}{%- if enable_thinking is defined and enable_thinking is false %}{{- '<think>
7
+
8
+ </think>
9
+
10
+ ' }}{%- endif %}{%- endif %}
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33bc7e10f3893cca5d37bdc21b020361cb1ead2b56605f59fdfb0f7c0fe81f3c
3
+ size 11422928
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "OvisImageTransformer2DModel",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "/mnt/disk4/lvl/Ovis-Image-7B/transformer",
5
+ "attention_head_dim": 128,
6
+ "axes_dims_rope": [
7
+ 16,
8
+ 56,
9
+ 56
10
+ ],
11
+ "in_channels": 64,
12
+ "joint_attention_dim": 2048,
13
+ "num_attention_heads": 24,
14
+ "num_layers": 6,
15
+ "num_single_layers": 27,
16
+ "out_channels": null,
17
+ "patch_size": 1,
18
+ "quantization_config": {
19
+ "autoround_version": "0.13.0",
20
+ "batch_size": 1,
21
+ "bits": 4,
22
+ "block_name_to_quantize": "transformer_blocks,single_transformer_blocks",
23
+ "data_type": "int",
24
+ "group_size": 128,
25
+ "nsamples": 64,
26
+ "packing_format": "auto_round:auto_gptq",
27
+ "quant_method": "auto-round",
28
+ "sym": true
29
+ }
30
+ }
transformer/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c644ad50fc2028d386afe76ae55d23059e904c83888c5536148c292cfdd3f7
3
+ size 1060229568
transformer/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ccde8041d288dfdc3d9cd86cae07a5aabef1375a4b9b0f6805984c6fa739e0
3
+ size 1069937984
transformer/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d5de5630637a801c97d2eb61ff80838350920e449a535c8e2d82c531129899d
3
+ size 1045399264
transformer/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502e35a22123ded86e969c749e05c719035a72ff0a5df01eca50064ed897580f
3
+ size 709637512
transformer/model.safetensors.index.json ADDED
@@ -0,0 +1,1085 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "format": "safetensors",
4
+ "total_shards": 4,
5
+ "total_parameters": 1018791744,
6
+ "total_size": 3885078144
7
+ },
8
+ "weight_map": {
9
+ "transformer_blocks.0.norm1.linear.qweight": "model-00001-of-00004.safetensors",
10
+ "transformer_blocks.0.norm1.linear.qzeros": "model-00001-of-00004.safetensors",
11
+ "transformer_blocks.0.norm1.linear.scales": "model-00001-of-00004.safetensors",
12
+ "transformer_blocks.0.norm1.linear.bias": "model-00001-of-00004.safetensors",
13
+ "transformer_blocks.0.norm1_context.linear.qweight": "model-00001-of-00004.safetensors",
14
+ "transformer_blocks.0.norm1_context.linear.qzeros": "model-00001-of-00004.safetensors",
15
+ "transformer_blocks.0.norm1_context.linear.scales": "model-00001-of-00004.safetensors",
16
+ "transformer_blocks.0.norm1_context.linear.bias": "model-00001-of-00004.safetensors",
17
+ "transformer_blocks.0.attn.norm_q.weight": "model-00001-of-00004.safetensors",
18
+ "transformer_blocks.0.attn.norm_k.weight": "model-00001-of-00004.safetensors",
19
+ "transformer_blocks.0.attn.to_q.qweight": "model-00001-of-00004.safetensors",
20
+ "transformer_blocks.0.attn.to_q.qzeros": "model-00001-of-00004.safetensors",
21
+ "transformer_blocks.0.attn.to_q.scales": "model-00001-of-00004.safetensors",
22
+ "transformer_blocks.0.attn.to_q.bias": "model-00001-of-00004.safetensors",
23
+ "transformer_blocks.0.attn.to_k.qweight": "model-00001-of-00004.safetensors",
24
+ "transformer_blocks.0.attn.to_k.qzeros": "model-00001-of-00004.safetensors",
25
+ "transformer_blocks.0.attn.to_k.scales": "model-00001-of-00004.safetensors",
26
+ "transformer_blocks.0.attn.to_k.bias": "model-00001-of-00004.safetensors",
27
+ "transformer_blocks.0.attn.to_v.qweight": "model-00001-of-00004.safetensors",
28
+ "transformer_blocks.0.attn.to_v.qzeros": "model-00001-of-00004.safetensors",
29
+ "transformer_blocks.0.attn.to_v.scales": "model-00001-of-00004.safetensors",
30
+ "transformer_blocks.0.attn.to_v.bias": "model-00001-of-00004.safetensors",
31
+ "transformer_blocks.0.attn.to_out.0.qweight": "model-00001-of-00004.safetensors",
32
+ "transformer_blocks.0.attn.to_out.0.qzeros": "model-00001-of-00004.safetensors",
33
+ "transformer_blocks.0.attn.to_out.0.scales": "model-00001-of-00004.safetensors",
34
+ "transformer_blocks.0.attn.to_out.0.bias": "model-00001-of-00004.safetensors",
35
+ "transformer_blocks.0.attn.norm_added_q.weight": "model-00001-of-00004.safetensors",
36
+ "transformer_blocks.0.attn.norm_added_k.weight": "model-00001-of-00004.safetensors",
37
+ "transformer_blocks.0.attn.add_q_proj.qweight": "model-00001-of-00004.safetensors",
38
+ "transformer_blocks.0.attn.add_q_proj.qzeros": "model-00001-of-00004.safetensors",
39
+ "transformer_blocks.0.attn.add_q_proj.scales": "model-00001-of-00004.safetensors",
40
+ "transformer_blocks.0.attn.add_q_proj.bias": "model-00001-of-00004.safetensors",
41
+ "transformer_blocks.0.attn.add_k_proj.qweight": "model-00001-of-00004.safetensors",
42
+ "transformer_blocks.0.attn.add_k_proj.qzeros": "model-00001-of-00004.safetensors",
43
+ "transformer_blocks.0.attn.add_k_proj.scales": "model-00001-of-00004.safetensors",
44
+ "transformer_blocks.0.attn.add_k_proj.bias": "model-00001-of-00004.safetensors",
45
+ "transformer_blocks.0.attn.add_v_proj.qweight": "model-00001-of-00004.safetensors",
46
+ "transformer_blocks.0.attn.add_v_proj.qzeros": "model-00001-of-00004.safetensors",
47
+ "transformer_blocks.0.attn.add_v_proj.scales": "model-00001-of-00004.safetensors",
48
+ "transformer_blocks.0.attn.add_v_proj.bias": "model-00001-of-00004.safetensors",
49
+ "transformer_blocks.0.attn.to_add_out.qweight": "model-00001-of-00004.safetensors",
50
+ "transformer_blocks.0.attn.to_add_out.qzeros": "model-00001-of-00004.safetensors",
51
+ "transformer_blocks.0.attn.to_add_out.scales": "model-00001-of-00004.safetensors",
52
+ "transformer_blocks.0.attn.to_add_out.bias": "model-00001-of-00004.safetensors",
53
+ "transformer_blocks.0.ff.net.0.proj.qweight": "model-00001-of-00004.safetensors",
54
+ "transformer_blocks.0.ff.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
55
+ "transformer_blocks.0.ff.net.0.proj.scales": "model-00001-of-00004.safetensors",
56
+ "transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00004.safetensors",
57
+ "transformer_blocks.0.ff.net.2.qweight": "model-00001-of-00004.safetensors",
58
+ "transformer_blocks.0.ff.net.2.qzeros": "model-00001-of-00004.safetensors",
59
+ "transformer_blocks.0.ff.net.2.scales": "model-00001-of-00004.safetensors",
60
+ "transformer_blocks.0.ff.net.2.bias": "model-00001-of-00004.safetensors",
61
+ "transformer_blocks.0.ff_context.net.0.proj.qweight": "model-00001-of-00004.safetensors",
62
+ "transformer_blocks.0.ff_context.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
63
+ "transformer_blocks.0.ff_context.net.0.proj.scales": "model-00001-of-00004.safetensors",
64
+ "transformer_blocks.0.ff_context.net.0.proj.bias": "model-00001-of-00004.safetensors",
65
+ "transformer_blocks.0.ff_context.net.2.qweight": "model-00001-of-00004.safetensors",
66
+ "transformer_blocks.0.ff_context.net.2.qzeros": "model-00001-of-00004.safetensors",
67
+ "transformer_blocks.0.ff_context.net.2.scales": "model-00001-of-00004.safetensors",
68
+ "transformer_blocks.0.ff_context.net.2.bias": "model-00001-of-00004.safetensors",
69
+ "transformer_blocks.1.norm1.linear.qweight": "model-00001-of-00004.safetensors",
70
+ "transformer_blocks.1.norm1.linear.qzeros": "model-00001-of-00004.safetensors",
71
+ "transformer_blocks.1.norm1.linear.scales": "model-00001-of-00004.safetensors",
72
+ "transformer_blocks.1.norm1.linear.bias": "model-00001-of-00004.safetensors",
73
+ "transformer_blocks.1.norm1_context.linear.qweight": "model-00001-of-00004.safetensors",
74
+ "transformer_blocks.1.norm1_context.linear.qzeros": "model-00001-of-00004.safetensors",
75
+ "transformer_blocks.1.norm1_context.linear.scales": "model-00001-of-00004.safetensors",
76
+ "transformer_blocks.1.norm1_context.linear.bias": "model-00001-of-00004.safetensors",
77
+ "transformer_blocks.1.attn.norm_q.weight": "model-00001-of-00004.safetensors",
78
+ "transformer_blocks.1.attn.norm_k.weight": "model-00001-of-00004.safetensors",
79
+ "transformer_blocks.1.attn.to_q.qweight": "model-00001-of-00004.safetensors",
80
+ "transformer_blocks.1.attn.to_q.qzeros": "model-00001-of-00004.safetensors",
81
+ "transformer_blocks.1.attn.to_q.scales": "model-00001-of-00004.safetensors",
82
+ "transformer_blocks.1.attn.to_q.bias": "model-00001-of-00004.safetensors",
83
+ "transformer_blocks.1.attn.to_k.qweight": "model-00001-of-00004.safetensors",
84
+ "transformer_blocks.1.attn.to_k.qzeros": "model-00001-of-00004.safetensors",
85
+ "transformer_blocks.1.attn.to_k.scales": "model-00001-of-00004.safetensors",
86
+ "transformer_blocks.1.attn.to_k.bias": "model-00001-of-00004.safetensors",
87
+ "transformer_blocks.1.attn.to_v.qweight": "model-00001-of-00004.safetensors",
88
+ "transformer_blocks.1.attn.to_v.qzeros": "model-00001-of-00004.safetensors",
89
+ "transformer_blocks.1.attn.to_v.scales": "model-00001-of-00004.safetensors",
90
+ "transformer_blocks.1.attn.to_v.bias": "model-00001-of-00004.safetensors",
91
+ "transformer_blocks.1.attn.to_out.0.qweight": "model-00001-of-00004.safetensors",
92
+ "transformer_blocks.1.attn.to_out.0.qzeros": "model-00001-of-00004.safetensors",
93
+ "transformer_blocks.1.attn.to_out.0.scales": "model-00001-of-00004.safetensors",
94
+ "transformer_blocks.1.attn.to_out.0.bias": "model-00001-of-00004.safetensors",
95
+ "transformer_blocks.1.attn.norm_added_q.weight": "model-00001-of-00004.safetensors",
96
+ "transformer_blocks.1.attn.norm_added_k.weight": "model-00001-of-00004.safetensors",
97
+ "transformer_blocks.1.attn.add_q_proj.qweight": "model-00001-of-00004.safetensors",
98
+ "transformer_blocks.1.attn.add_q_proj.qzeros": "model-00001-of-00004.safetensors",
99
+ "transformer_blocks.1.attn.add_q_proj.scales": "model-00001-of-00004.safetensors",
100
+ "transformer_blocks.1.attn.add_q_proj.bias": "model-00001-of-00004.safetensors",
101
+ "transformer_blocks.1.attn.add_k_proj.qweight": "model-00001-of-00004.safetensors",
102
+ "transformer_blocks.1.attn.add_k_proj.qzeros": "model-00001-of-00004.safetensors",
103
+ "transformer_blocks.1.attn.add_k_proj.scales": "model-00001-of-00004.safetensors",
104
+ "transformer_blocks.1.attn.add_k_proj.bias": "model-00001-of-00004.safetensors",
105
+ "transformer_blocks.1.attn.add_v_proj.qweight": "model-00001-of-00004.safetensors",
106
+ "transformer_blocks.1.attn.add_v_proj.qzeros": "model-00001-of-00004.safetensors",
107
+ "transformer_blocks.1.attn.add_v_proj.scales": "model-00001-of-00004.safetensors",
108
+ "transformer_blocks.1.attn.add_v_proj.bias": "model-00001-of-00004.safetensors",
109
+ "transformer_blocks.1.attn.to_add_out.qweight": "model-00001-of-00004.safetensors",
110
+ "transformer_blocks.1.attn.to_add_out.qzeros": "model-00001-of-00004.safetensors",
111
+ "transformer_blocks.1.attn.to_add_out.scales": "model-00001-of-00004.safetensors",
112
+ "transformer_blocks.1.attn.to_add_out.bias": "model-00001-of-00004.safetensors",
113
+ "transformer_blocks.1.ff.net.0.proj.qweight": "model-00001-of-00004.safetensors",
114
+ "transformer_blocks.1.ff.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
115
+ "transformer_blocks.1.ff.net.0.proj.scales": "model-00001-of-00004.safetensors",
116
+ "transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00004.safetensors",
117
+ "transformer_blocks.1.ff.net.2.qweight": "model-00001-of-00004.safetensors",
118
+ "transformer_blocks.1.ff.net.2.qzeros": "model-00001-of-00004.safetensors",
119
+ "transformer_blocks.1.ff.net.2.scales": "model-00001-of-00004.safetensors",
120
+ "transformer_blocks.1.ff.net.2.bias": "model-00001-of-00004.safetensors",
121
+ "transformer_blocks.1.ff_context.net.0.proj.qweight": "model-00001-of-00004.safetensors",
122
+ "transformer_blocks.1.ff_context.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
123
+ "transformer_blocks.1.ff_context.net.0.proj.scales": "model-00001-of-00004.safetensors",
124
+ "transformer_blocks.1.ff_context.net.0.proj.bias": "model-00001-of-00004.safetensors",
125
+ "transformer_blocks.1.ff_context.net.2.qweight": "model-00001-of-00004.safetensors",
126
+ "transformer_blocks.1.ff_context.net.2.qzeros": "model-00001-of-00004.safetensors",
127
+ "transformer_blocks.1.ff_context.net.2.scales": "model-00001-of-00004.safetensors",
128
+ "transformer_blocks.1.ff_context.net.2.bias": "model-00001-of-00004.safetensors",
129
+ "transformer_blocks.2.norm1.linear.qweight": "model-00001-of-00004.safetensors",
130
+ "transformer_blocks.2.norm1.linear.qzeros": "model-00001-of-00004.safetensors",
131
+ "transformer_blocks.2.norm1.linear.scales": "model-00001-of-00004.safetensors",
132
+ "transformer_blocks.2.norm1.linear.bias": "model-00001-of-00004.safetensors",
133
+ "transformer_blocks.2.norm1_context.linear.qweight": "model-00001-of-00004.safetensors",
134
+ "transformer_blocks.2.norm1_context.linear.qzeros": "model-00001-of-00004.safetensors",
135
+ "transformer_blocks.2.norm1_context.linear.scales": "model-00001-of-00004.safetensors",
136
+ "transformer_blocks.2.norm1_context.linear.bias": "model-00001-of-00004.safetensors",
137
+ "transformer_blocks.2.attn.norm_q.weight": "model-00001-of-00004.safetensors",
138
+ "transformer_blocks.2.attn.norm_k.weight": "model-00001-of-00004.safetensors",
139
+ "transformer_blocks.2.attn.to_q.qweight": "model-00001-of-00004.safetensors",
140
+ "transformer_blocks.2.attn.to_q.qzeros": "model-00001-of-00004.safetensors",
141
+ "transformer_blocks.2.attn.to_q.scales": "model-00001-of-00004.safetensors",
142
+ "transformer_blocks.2.attn.to_q.bias": "model-00001-of-00004.safetensors",
143
+ "transformer_blocks.2.attn.to_k.qweight": "model-00001-of-00004.safetensors",
144
+ "transformer_blocks.2.attn.to_k.qzeros": "model-00001-of-00004.safetensors",
145
+ "transformer_blocks.2.attn.to_k.scales": "model-00001-of-00004.safetensors",
146
+ "transformer_blocks.2.attn.to_k.bias": "model-00001-of-00004.safetensors",
147
+ "transformer_blocks.2.attn.to_v.qweight": "model-00001-of-00004.safetensors",
148
+ "transformer_blocks.2.attn.to_v.qzeros": "model-00001-of-00004.safetensors",
149
+ "transformer_blocks.2.attn.to_v.scales": "model-00001-of-00004.safetensors",
150
+ "transformer_blocks.2.attn.to_v.bias": "model-00001-of-00004.safetensors",
151
+ "transformer_blocks.2.attn.to_out.0.qweight": "model-00001-of-00004.safetensors",
152
+ "transformer_blocks.2.attn.to_out.0.qzeros": "model-00001-of-00004.safetensors",
153
+ "transformer_blocks.2.attn.to_out.0.scales": "model-00001-of-00004.safetensors",
154
+ "transformer_blocks.2.attn.to_out.0.bias": "model-00001-of-00004.safetensors",
155
+ "transformer_blocks.2.attn.norm_added_q.weight": "model-00001-of-00004.safetensors",
156
+ "transformer_blocks.2.attn.norm_added_k.weight": "model-00001-of-00004.safetensors",
157
+ "transformer_blocks.2.attn.add_q_proj.qweight": "model-00001-of-00004.safetensors",
158
+ "transformer_blocks.2.attn.add_q_proj.qzeros": "model-00001-of-00004.safetensors",
159
+ "transformer_blocks.2.attn.add_q_proj.scales": "model-00001-of-00004.safetensors",
160
+ "transformer_blocks.2.attn.add_q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "transformer_blocks.2.attn.add_k_proj.qweight": "model-00001-of-00004.safetensors",
162
+ "transformer_blocks.2.attn.add_k_proj.qzeros": "model-00001-of-00004.safetensors",
163
+ "transformer_blocks.2.attn.add_k_proj.scales": "model-00001-of-00004.safetensors",
164
+ "transformer_blocks.2.attn.add_k_proj.bias": "model-00001-of-00004.safetensors",
165
+ "transformer_blocks.2.attn.add_v_proj.qweight": "model-00001-of-00004.safetensors",
166
+ "transformer_blocks.2.attn.add_v_proj.qzeros": "model-00001-of-00004.safetensors",
167
+ "transformer_blocks.2.attn.add_v_proj.scales": "model-00001-of-00004.safetensors",
168
+ "transformer_blocks.2.attn.add_v_proj.bias": "model-00001-of-00004.safetensors",
169
+ "transformer_blocks.2.attn.to_add_out.qweight": "model-00001-of-00004.safetensors",
170
+ "transformer_blocks.2.attn.to_add_out.qzeros": "model-00001-of-00004.safetensors",
171
+ "transformer_blocks.2.attn.to_add_out.scales": "model-00001-of-00004.safetensors",
172
+ "transformer_blocks.2.attn.to_add_out.bias": "model-00001-of-00004.safetensors",
173
+ "transformer_blocks.2.ff.net.0.proj.qweight": "model-00001-of-00004.safetensors",
174
+ "transformer_blocks.2.ff.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
175
+ "transformer_blocks.2.ff.net.0.proj.scales": "model-00001-of-00004.safetensors",
176
+ "transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00004.safetensors",
177
+ "transformer_blocks.2.ff.net.2.qweight": "model-00001-of-00004.safetensors",
178
+ "transformer_blocks.2.ff.net.2.qzeros": "model-00001-of-00004.safetensors",
179
+ "transformer_blocks.2.ff.net.2.scales": "model-00001-of-00004.safetensors",
180
+ "transformer_blocks.2.ff.net.2.bias": "model-00001-of-00004.safetensors",
181
+ "transformer_blocks.2.ff_context.net.0.proj.qweight": "model-00001-of-00004.safetensors",
182
+ "transformer_blocks.2.ff_context.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
183
+ "transformer_blocks.2.ff_context.net.0.proj.scales": "model-00001-of-00004.safetensors",
184
+ "transformer_blocks.2.ff_context.net.0.proj.bias": "model-00001-of-00004.safetensors",
185
+ "transformer_blocks.2.ff_context.net.2.qweight": "model-00001-of-00004.safetensors",
186
+ "transformer_blocks.2.ff_context.net.2.qzeros": "model-00001-of-00004.safetensors",
187
+ "transformer_blocks.2.ff_context.net.2.scales": "model-00001-of-00004.safetensors",
188
+ "transformer_blocks.2.ff_context.net.2.bias": "model-00001-of-00004.safetensors",
189
+ "transformer_blocks.3.norm1.linear.qweight": "model-00001-of-00004.safetensors",
190
+ "transformer_blocks.3.norm1.linear.qzeros": "model-00001-of-00004.safetensors",
191
+ "transformer_blocks.3.norm1.linear.scales": "model-00001-of-00004.safetensors",
192
+ "transformer_blocks.3.norm1.linear.bias": "model-00001-of-00004.safetensors",
193
+ "transformer_blocks.3.norm1_context.linear.qweight": "model-00001-of-00004.safetensors",
194
+ "transformer_blocks.3.norm1_context.linear.qzeros": "model-00001-of-00004.safetensors",
195
+ "transformer_blocks.3.norm1_context.linear.scales": "model-00001-of-00004.safetensors",
196
+ "transformer_blocks.3.norm1_context.linear.bias": "model-00001-of-00004.safetensors",
197
+ "transformer_blocks.3.attn.norm_q.weight": "model-00001-of-00004.safetensors",
198
+ "transformer_blocks.3.attn.norm_k.weight": "model-00001-of-00004.safetensors",
199
+ "transformer_blocks.3.attn.to_q.qweight": "model-00001-of-00004.safetensors",
200
+ "transformer_blocks.3.attn.to_q.qzeros": "model-00001-of-00004.safetensors",
201
+ "transformer_blocks.3.attn.to_q.scales": "model-00001-of-00004.safetensors",
202
+ "transformer_blocks.3.attn.to_q.bias": "model-00001-of-00004.safetensors",
203
+ "transformer_blocks.3.attn.to_k.qweight": "model-00001-of-00004.safetensors",
204
+ "transformer_blocks.3.attn.to_k.qzeros": "model-00001-of-00004.safetensors",
205
+ "transformer_blocks.3.attn.to_k.scales": "model-00001-of-00004.safetensors",
206
+ "transformer_blocks.3.attn.to_k.bias": "model-00001-of-00004.safetensors",
207
+ "transformer_blocks.3.attn.to_v.qweight": "model-00001-of-00004.safetensors",
208
+ "transformer_blocks.3.attn.to_v.qzeros": "model-00001-of-00004.safetensors",
209
+ "transformer_blocks.3.attn.to_v.scales": "model-00001-of-00004.safetensors",
210
+ "transformer_blocks.3.attn.to_v.bias": "model-00001-of-00004.safetensors",
211
+ "transformer_blocks.3.attn.to_out.0.qweight": "model-00001-of-00004.safetensors",
212
+ "transformer_blocks.3.attn.to_out.0.qzeros": "model-00001-of-00004.safetensors",
213
+ "transformer_blocks.3.attn.to_out.0.scales": "model-00001-of-00004.safetensors",
214
+ "transformer_blocks.3.attn.to_out.0.bias": "model-00001-of-00004.safetensors",
215
+ "transformer_blocks.3.attn.norm_added_q.weight": "model-00001-of-00004.safetensors",
216
+ "transformer_blocks.3.attn.norm_added_k.weight": "model-00001-of-00004.safetensors",
217
+ "transformer_blocks.3.attn.add_q_proj.qweight": "model-00001-of-00004.safetensors",
218
+ "transformer_blocks.3.attn.add_q_proj.qzeros": "model-00001-of-00004.safetensors",
219
+ "transformer_blocks.3.attn.add_q_proj.scales": "model-00001-of-00004.safetensors",
220
+ "transformer_blocks.3.attn.add_q_proj.bias": "model-00001-of-00004.safetensors",
221
+ "transformer_blocks.3.attn.add_k_proj.qweight": "model-00001-of-00004.safetensors",
222
+ "transformer_blocks.3.attn.add_k_proj.qzeros": "model-00001-of-00004.safetensors",
223
+ "transformer_blocks.3.attn.add_k_proj.scales": "model-00001-of-00004.safetensors",
224
+ "transformer_blocks.3.attn.add_k_proj.bias": "model-00001-of-00004.safetensors",
225
+ "transformer_blocks.3.attn.add_v_proj.qweight": "model-00001-of-00004.safetensors",
226
+ "transformer_blocks.3.attn.add_v_proj.qzeros": "model-00001-of-00004.safetensors",
227
+ "transformer_blocks.3.attn.add_v_proj.scales": "model-00001-of-00004.safetensors",
228
+ "transformer_blocks.3.attn.add_v_proj.bias": "model-00001-of-00004.safetensors",
229
+ "transformer_blocks.3.attn.to_add_out.qweight": "model-00001-of-00004.safetensors",
230
+ "transformer_blocks.3.attn.to_add_out.qzeros": "model-00001-of-00004.safetensors",
231
+ "transformer_blocks.3.attn.to_add_out.scales": "model-00001-of-00004.safetensors",
232
+ "transformer_blocks.3.attn.to_add_out.bias": "model-00001-of-00004.safetensors",
233
+ "transformer_blocks.3.ff.net.0.proj.qweight": "model-00001-of-00004.safetensors",
234
+ "transformer_blocks.3.ff.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
235
+ "transformer_blocks.3.ff.net.0.proj.scales": "model-00001-of-00004.safetensors",
236
+ "transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00004.safetensors",
237
+ "transformer_blocks.3.ff.net.2.qweight": "model-00001-of-00004.safetensors",
238
+ "transformer_blocks.3.ff.net.2.qzeros": "model-00001-of-00004.safetensors",
239
+ "transformer_blocks.3.ff.net.2.scales": "model-00001-of-00004.safetensors",
240
+ "transformer_blocks.3.ff.net.2.bias": "model-00001-of-00004.safetensors",
241
+ "transformer_blocks.3.ff_context.net.0.proj.qweight": "model-00001-of-00004.safetensors",
242
+ "transformer_blocks.3.ff_context.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
243
+ "transformer_blocks.3.ff_context.net.0.proj.scales": "model-00001-of-00004.safetensors",
244
+ "transformer_blocks.3.ff_context.net.0.proj.bias": "model-00001-of-00004.safetensors",
245
+ "transformer_blocks.3.ff_context.net.2.qweight": "model-00001-of-00004.safetensors",
246
+ "transformer_blocks.3.ff_context.net.2.qzeros": "model-00001-of-00004.safetensors",
247
+ "transformer_blocks.3.ff_context.net.2.scales": "model-00001-of-00004.safetensors",
248
+ "transformer_blocks.3.ff_context.net.2.bias": "model-00001-of-00004.safetensors",
249
+ "transformer_blocks.4.norm1.linear.qweight": "model-00001-of-00004.safetensors",
250
+ "transformer_blocks.4.norm1.linear.qzeros": "model-00001-of-00004.safetensors",
251
+ "transformer_blocks.4.norm1.linear.scales": "model-00001-of-00004.safetensors",
252
+ "transformer_blocks.4.norm1.linear.bias": "model-00001-of-00004.safetensors",
253
+ "transformer_blocks.4.norm1_context.linear.qweight": "model-00001-of-00004.safetensors",
254
+ "transformer_blocks.4.norm1_context.linear.qzeros": "model-00001-of-00004.safetensors",
255
+ "transformer_blocks.4.norm1_context.linear.scales": "model-00001-of-00004.safetensors",
256
+ "transformer_blocks.4.norm1_context.linear.bias": "model-00001-of-00004.safetensors",
257
+ "transformer_blocks.4.attn.norm_q.weight": "model-00001-of-00004.safetensors",
258
+ "transformer_blocks.4.attn.norm_k.weight": "model-00001-of-00004.safetensors",
259
+ "transformer_blocks.4.attn.to_q.qweight": "model-00001-of-00004.safetensors",
260
+ "transformer_blocks.4.attn.to_q.qzeros": "model-00001-of-00004.safetensors",
261
+ "transformer_blocks.4.attn.to_q.scales": "model-00001-of-00004.safetensors",
262
+ "transformer_blocks.4.attn.to_q.bias": "model-00001-of-00004.safetensors",
263
+ "transformer_blocks.4.attn.to_k.qweight": "model-00001-of-00004.safetensors",
264
+ "transformer_blocks.4.attn.to_k.qzeros": "model-00001-of-00004.safetensors",
265
+ "transformer_blocks.4.attn.to_k.scales": "model-00001-of-00004.safetensors",
266
+ "transformer_blocks.4.attn.to_k.bias": "model-00001-of-00004.safetensors",
267
+ "transformer_blocks.4.attn.to_v.qweight": "model-00001-of-00004.safetensors",
268
+ "transformer_blocks.4.attn.to_v.qzeros": "model-00001-of-00004.safetensors",
269
+ "transformer_blocks.4.attn.to_v.scales": "model-00001-of-00004.safetensors",
270
+ "transformer_blocks.4.attn.to_v.bias": "model-00001-of-00004.safetensors",
271
+ "transformer_blocks.4.attn.to_out.0.qweight": "model-00001-of-00004.safetensors",
272
+ "transformer_blocks.4.attn.to_out.0.qzeros": "model-00001-of-00004.safetensors",
273
+ "transformer_blocks.4.attn.to_out.0.scales": "model-00001-of-00004.safetensors",
274
+ "transformer_blocks.4.attn.to_out.0.bias": "model-00001-of-00004.safetensors",
275
+ "transformer_blocks.4.attn.norm_added_q.weight": "model-00001-of-00004.safetensors",
276
+ "transformer_blocks.4.attn.norm_added_k.weight": "model-00001-of-00004.safetensors",
277
+ "transformer_blocks.4.attn.add_q_proj.qweight": "model-00001-of-00004.safetensors",
278
+ "transformer_blocks.4.attn.add_q_proj.qzeros": "model-00001-of-00004.safetensors",
279
+ "transformer_blocks.4.attn.add_q_proj.scales": "model-00001-of-00004.safetensors",
280
+ "transformer_blocks.4.attn.add_q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "transformer_blocks.4.attn.add_k_proj.qweight": "model-00001-of-00004.safetensors",
282
+ "transformer_blocks.4.attn.add_k_proj.qzeros": "model-00001-of-00004.safetensors",
283
+ "transformer_blocks.4.attn.add_k_proj.scales": "model-00001-of-00004.safetensors",
284
+ "transformer_blocks.4.attn.add_k_proj.bias": "model-00001-of-00004.safetensors",
285
+ "transformer_blocks.4.attn.add_v_proj.qweight": "model-00001-of-00004.safetensors",
286
+ "transformer_blocks.4.attn.add_v_proj.qzeros": "model-00001-of-00004.safetensors",
287
+ "transformer_blocks.4.attn.add_v_proj.scales": "model-00001-of-00004.safetensors",
288
+ "transformer_blocks.4.attn.add_v_proj.bias": "model-00001-of-00004.safetensors",
289
+ "transformer_blocks.4.attn.to_add_out.qweight": "model-00001-of-00004.safetensors",
290
+ "transformer_blocks.4.attn.to_add_out.qzeros": "model-00001-of-00004.safetensors",
291
+ "transformer_blocks.4.attn.to_add_out.scales": "model-00001-of-00004.safetensors",
292
+ "transformer_blocks.4.attn.to_add_out.bias": "model-00001-of-00004.safetensors",
293
+ "transformer_blocks.4.ff.net.0.proj.qweight": "model-00001-of-00004.safetensors",
294
+ "transformer_blocks.4.ff.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
295
+ "transformer_blocks.4.ff.net.0.proj.scales": "model-00001-of-00004.safetensors",
296
+ "transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00004.safetensors",
297
+ "transformer_blocks.4.ff.net.2.qweight": "model-00001-of-00004.safetensors",
298
+ "transformer_blocks.4.ff.net.2.qzeros": "model-00001-of-00004.safetensors",
299
+ "transformer_blocks.4.ff.net.2.scales": "model-00001-of-00004.safetensors",
300
+ "transformer_blocks.4.ff.net.2.bias": "model-00001-of-00004.safetensors",
301
+ "transformer_blocks.4.ff_context.net.0.proj.qweight": "model-00001-of-00004.safetensors",
302
+ "transformer_blocks.4.ff_context.net.0.proj.qzeros": "model-00001-of-00004.safetensors",
303
+ "transformer_blocks.4.ff_context.net.0.proj.scales": "model-00001-of-00004.safetensors",
304
+ "transformer_blocks.4.ff_context.net.0.proj.bias": "model-00001-of-00004.safetensors",
305
+ "transformer_blocks.4.ff_context.net.2.qweight": "model-00002-of-00004.safetensors",
306
+ "transformer_blocks.4.ff_context.net.2.qzeros": "model-00002-of-00004.safetensors",
307
+ "transformer_blocks.4.ff_context.net.2.scales": "model-00002-of-00004.safetensors",
308
+ "transformer_blocks.4.ff_context.net.2.bias": "model-00002-of-00004.safetensors",
309
+ "transformer_blocks.5.norm1.linear.qweight": "model-00002-of-00004.safetensors",
310
+ "transformer_blocks.5.norm1.linear.qzeros": "model-00002-of-00004.safetensors",
311
+ "transformer_blocks.5.norm1.linear.scales": "model-00002-of-00004.safetensors",
312
+ "transformer_blocks.5.norm1.linear.bias": "model-00002-of-00004.safetensors",
313
+ "transformer_blocks.5.norm1_context.linear.qweight": "model-00002-of-00004.safetensors",
314
+ "transformer_blocks.5.norm1_context.linear.qzeros": "model-00002-of-00004.safetensors",
315
+ "transformer_blocks.5.norm1_context.linear.scales": "model-00002-of-00004.safetensors",
316
+ "transformer_blocks.5.norm1_context.linear.bias": "model-00002-of-00004.safetensors",
317
+ "transformer_blocks.5.attn.norm_q.weight": "model-00002-of-00004.safetensors",
318
+ "transformer_blocks.5.attn.norm_k.weight": "model-00002-of-00004.safetensors",
319
+ "transformer_blocks.5.attn.to_q.qweight": "model-00002-of-00004.safetensors",
320
+ "transformer_blocks.5.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
321
+ "transformer_blocks.5.attn.to_q.scales": "model-00002-of-00004.safetensors",
322
+ "transformer_blocks.5.attn.to_q.bias": "model-00002-of-00004.safetensors",
323
+ "transformer_blocks.5.attn.to_k.qweight": "model-00002-of-00004.safetensors",
324
+ "transformer_blocks.5.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
325
+ "transformer_blocks.5.attn.to_k.scales": "model-00002-of-00004.safetensors",
326
+ "transformer_blocks.5.attn.to_k.bias": "model-00002-of-00004.safetensors",
327
+ "transformer_blocks.5.attn.to_v.qweight": "model-00002-of-00004.safetensors",
328
+ "transformer_blocks.5.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
329
+ "transformer_blocks.5.attn.to_v.scales": "model-00002-of-00004.safetensors",
330
+ "transformer_blocks.5.attn.to_v.bias": "model-00002-of-00004.safetensors",
331
+ "transformer_blocks.5.attn.to_out.0.qweight": "model-00002-of-00004.safetensors",
332
+ "transformer_blocks.5.attn.to_out.0.qzeros": "model-00002-of-00004.safetensors",
333
+ "transformer_blocks.5.attn.to_out.0.scales": "model-00002-of-00004.safetensors",
334
+ "transformer_blocks.5.attn.to_out.0.bias": "model-00002-of-00004.safetensors",
335
+ "transformer_blocks.5.attn.norm_added_q.weight": "model-00002-of-00004.safetensors",
336
+ "transformer_blocks.5.attn.norm_added_k.weight": "model-00002-of-00004.safetensors",
337
+ "transformer_blocks.5.attn.add_q_proj.qweight": "model-00002-of-00004.safetensors",
338
+ "transformer_blocks.5.attn.add_q_proj.qzeros": "model-00002-of-00004.safetensors",
339
+ "transformer_blocks.5.attn.add_q_proj.scales": "model-00002-of-00004.safetensors",
340
+ "transformer_blocks.5.attn.add_q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "transformer_blocks.5.attn.add_k_proj.qweight": "model-00002-of-00004.safetensors",
342
+ "transformer_blocks.5.attn.add_k_proj.qzeros": "model-00002-of-00004.safetensors",
343
+ "transformer_blocks.5.attn.add_k_proj.scales": "model-00002-of-00004.safetensors",
344
+ "transformer_blocks.5.attn.add_k_proj.bias": "model-00002-of-00004.safetensors",
345
+ "transformer_blocks.5.attn.add_v_proj.qweight": "model-00002-of-00004.safetensors",
346
+ "transformer_blocks.5.attn.add_v_proj.qzeros": "model-00002-of-00004.safetensors",
347
+ "transformer_blocks.5.attn.add_v_proj.scales": "model-00002-of-00004.safetensors",
348
+ "transformer_blocks.5.attn.add_v_proj.bias": "model-00002-of-00004.safetensors",
349
+ "transformer_blocks.5.attn.to_add_out.qweight": "model-00002-of-00004.safetensors",
350
+ "transformer_blocks.5.attn.to_add_out.qzeros": "model-00002-of-00004.safetensors",
351
+ "transformer_blocks.5.attn.to_add_out.scales": "model-00002-of-00004.safetensors",
352
+ "transformer_blocks.5.attn.to_add_out.bias": "model-00002-of-00004.safetensors",
353
+ "transformer_blocks.5.ff.net.0.proj.qweight": "model-00002-of-00004.safetensors",
354
+ "transformer_blocks.5.ff.net.0.proj.qzeros": "model-00002-of-00004.safetensors",
355
+ "transformer_blocks.5.ff.net.0.proj.scales": "model-00002-of-00004.safetensors",
356
+ "transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00004.safetensors",
357
+ "transformer_blocks.5.ff.net.2.qweight": "model-00002-of-00004.safetensors",
358
+ "transformer_blocks.5.ff.net.2.qzeros": "model-00002-of-00004.safetensors",
359
+ "transformer_blocks.5.ff.net.2.scales": "model-00002-of-00004.safetensors",
360
+ "transformer_blocks.5.ff.net.2.bias": "model-00002-of-00004.safetensors",
361
+ "transformer_blocks.5.ff_context.net.0.proj.qweight": "model-00002-of-00004.safetensors",
362
+ "transformer_blocks.5.ff_context.net.0.proj.qzeros": "model-00002-of-00004.safetensors",
363
+ "transformer_blocks.5.ff_context.net.0.proj.scales": "model-00002-of-00004.safetensors",
364
+ "transformer_blocks.5.ff_context.net.0.proj.bias": "model-00002-of-00004.safetensors",
365
+ "transformer_blocks.5.ff_context.net.2.qweight": "model-00002-of-00004.safetensors",
366
+ "transformer_blocks.5.ff_context.net.2.qzeros": "model-00002-of-00004.safetensors",
367
+ "transformer_blocks.5.ff_context.net.2.scales": "model-00002-of-00004.safetensors",
368
+ "transformer_blocks.5.ff_context.net.2.bias": "model-00002-of-00004.safetensors",
369
+ "single_transformer_blocks.0.norm.linear.qweight": "model-00002-of-00004.safetensors",
370
+ "single_transformer_blocks.0.norm.linear.qzeros": "model-00002-of-00004.safetensors",
371
+ "single_transformer_blocks.0.norm.linear.scales": "model-00002-of-00004.safetensors",
372
+ "single_transformer_blocks.0.norm.linear.bias": "model-00002-of-00004.safetensors",
373
+ "single_transformer_blocks.0.proj_mlp.qweight": "model-00002-of-00004.safetensors",
374
+ "single_transformer_blocks.0.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
375
+ "single_transformer_blocks.0.proj_mlp.scales": "model-00002-of-00004.safetensors",
376
+ "single_transformer_blocks.0.proj_mlp.bias": "model-00002-of-00004.safetensors",
377
+ "single_transformer_blocks.0.proj_out.qweight": "model-00002-of-00004.safetensors",
378
+ "single_transformer_blocks.0.proj_out.qzeros": "model-00002-of-00004.safetensors",
379
+ "single_transformer_blocks.0.proj_out.scales": "model-00002-of-00004.safetensors",
380
+ "single_transformer_blocks.0.proj_out.bias": "model-00002-of-00004.safetensors",
381
+ "single_transformer_blocks.0.attn.norm_q.weight": "model-00002-of-00004.safetensors",
382
+ "single_transformer_blocks.0.attn.norm_k.weight": "model-00002-of-00004.safetensors",
383
+ "single_transformer_blocks.0.attn.to_q.qweight": "model-00002-of-00004.safetensors",
384
+ "single_transformer_blocks.0.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
385
+ "single_transformer_blocks.0.attn.to_q.scales": "model-00002-of-00004.safetensors",
386
+ "single_transformer_blocks.0.attn.to_q.bias": "model-00002-of-00004.safetensors",
387
+ "single_transformer_blocks.0.attn.to_k.qweight": "model-00002-of-00004.safetensors",
388
+ "single_transformer_blocks.0.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
389
+ "single_transformer_blocks.0.attn.to_k.scales": "model-00002-of-00004.safetensors",
390
+ "single_transformer_blocks.0.attn.to_k.bias": "model-00002-of-00004.safetensors",
391
+ "single_transformer_blocks.0.attn.to_v.qweight": "model-00002-of-00004.safetensors",
392
+ "single_transformer_blocks.0.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
393
+ "single_transformer_blocks.0.attn.to_v.scales": "model-00002-of-00004.safetensors",
394
+ "single_transformer_blocks.0.attn.to_v.bias": "model-00002-of-00004.safetensors",
395
+ "single_transformer_blocks.1.norm.linear.qweight": "model-00002-of-00004.safetensors",
396
+ "single_transformer_blocks.1.norm.linear.qzeros": "model-00002-of-00004.safetensors",
397
+ "single_transformer_blocks.1.norm.linear.scales": "model-00002-of-00004.safetensors",
398
+ "single_transformer_blocks.1.norm.linear.bias": "model-00002-of-00004.safetensors",
399
+ "single_transformer_blocks.1.proj_mlp.qweight": "model-00002-of-00004.safetensors",
400
+ "single_transformer_blocks.1.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
401
+ "single_transformer_blocks.1.proj_mlp.scales": "model-00002-of-00004.safetensors",
402
+ "single_transformer_blocks.1.proj_mlp.bias": "model-00002-of-00004.safetensors",
403
+ "single_transformer_blocks.1.proj_out.qweight": "model-00002-of-00004.safetensors",
404
+ "single_transformer_blocks.1.proj_out.qzeros": "model-00002-of-00004.safetensors",
405
+ "single_transformer_blocks.1.proj_out.scales": "model-00002-of-00004.safetensors",
406
+ "single_transformer_blocks.1.proj_out.bias": "model-00002-of-00004.safetensors",
407
+ "single_transformer_blocks.1.attn.norm_q.weight": "model-00002-of-00004.safetensors",
408
+ "single_transformer_blocks.1.attn.norm_k.weight": "model-00002-of-00004.safetensors",
409
+ "single_transformer_blocks.1.attn.to_q.qweight": "model-00002-of-00004.safetensors",
410
+ "single_transformer_blocks.1.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
411
+ "single_transformer_blocks.1.attn.to_q.scales": "model-00002-of-00004.safetensors",
412
+ "single_transformer_blocks.1.attn.to_q.bias": "model-00002-of-00004.safetensors",
413
+ "single_transformer_blocks.1.attn.to_k.qweight": "model-00002-of-00004.safetensors",
414
+ "single_transformer_blocks.1.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
415
+ "single_transformer_blocks.1.attn.to_k.scales": "model-00002-of-00004.safetensors",
416
+ "single_transformer_blocks.1.attn.to_k.bias": "model-00002-of-00004.safetensors",
417
+ "single_transformer_blocks.1.attn.to_v.qweight": "model-00002-of-00004.safetensors",
418
+ "single_transformer_blocks.1.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
419
+ "single_transformer_blocks.1.attn.to_v.scales": "model-00002-of-00004.safetensors",
420
+ "single_transformer_blocks.1.attn.to_v.bias": "model-00002-of-00004.safetensors",
421
+ "single_transformer_blocks.2.norm.linear.qweight": "model-00002-of-00004.safetensors",
422
+ "single_transformer_blocks.2.norm.linear.qzeros": "model-00002-of-00004.safetensors",
423
+ "single_transformer_blocks.2.norm.linear.scales": "model-00002-of-00004.safetensors",
424
+ "single_transformer_blocks.2.norm.linear.bias": "model-00002-of-00004.safetensors",
425
+ "single_transformer_blocks.2.proj_mlp.qweight": "model-00002-of-00004.safetensors",
426
+ "single_transformer_blocks.2.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
427
+ "single_transformer_blocks.2.proj_mlp.scales": "model-00002-of-00004.safetensors",
428
+ "single_transformer_blocks.2.proj_mlp.bias": "model-00002-of-00004.safetensors",
429
+ "single_transformer_blocks.2.proj_out.qweight": "model-00002-of-00004.safetensors",
430
+ "single_transformer_blocks.2.proj_out.qzeros": "model-00002-of-00004.safetensors",
431
+ "single_transformer_blocks.2.proj_out.scales": "model-00002-of-00004.safetensors",
432
+ "single_transformer_blocks.2.proj_out.bias": "model-00002-of-00004.safetensors",
433
+ "single_transformer_blocks.2.attn.norm_q.weight": "model-00002-of-00004.safetensors",
434
+ "single_transformer_blocks.2.attn.norm_k.weight": "model-00002-of-00004.safetensors",
435
+ "single_transformer_blocks.2.attn.to_q.qweight": "model-00002-of-00004.safetensors",
436
+ "single_transformer_blocks.2.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
437
+ "single_transformer_blocks.2.attn.to_q.scales": "model-00002-of-00004.safetensors",
438
+ "single_transformer_blocks.2.attn.to_q.bias": "model-00002-of-00004.safetensors",
439
+ "single_transformer_blocks.2.attn.to_k.qweight": "model-00002-of-00004.safetensors",
440
+ "single_transformer_blocks.2.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
441
+ "single_transformer_blocks.2.attn.to_k.scales": "model-00002-of-00004.safetensors",
442
+ "single_transformer_blocks.2.attn.to_k.bias": "model-00002-of-00004.safetensors",
443
+ "single_transformer_blocks.2.attn.to_v.qweight": "model-00002-of-00004.safetensors",
444
+ "single_transformer_blocks.2.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
445
+ "single_transformer_blocks.2.attn.to_v.scales": "model-00002-of-00004.safetensors",
446
+ "single_transformer_blocks.2.attn.to_v.bias": "model-00002-of-00004.safetensors",
447
+ "single_transformer_blocks.3.norm.linear.qweight": "model-00002-of-00004.safetensors",
448
+ "single_transformer_blocks.3.norm.linear.qzeros": "model-00002-of-00004.safetensors",
449
+ "single_transformer_blocks.3.norm.linear.scales": "model-00002-of-00004.safetensors",
450
+ "single_transformer_blocks.3.norm.linear.bias": "model-00002-of-00004.safetensors",
451
+ "single_transformer_blocks.3.proj_mlp.qweight": "model-00002-of-00004.safetensors",
452
+ "single_transformer_blocks.3.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
453
+ "single_transformer_blocks.3.proj_mlp.scales": "model-00002-of-00004.safetensors",
454
+ "single_transformer_blocks.3.proj_mlp.bias": "model-00002-of-00004.safetensors",
455
+ "single_transformer_blocks.3.proj_out.qweight": "model-00002-of-00004.safetensors",
456
+ "single_transformer_blocks.3.proj_out.qzeros": "model-00002-of-00004.safetensors",
457
+ "single_transformer_blocks.3.proj_out.scales": "model-00002-of-00004.safetensors",
458
+ "single_transformer_blocks.3.proj_out.bias": "model-00002-of-00004.safetensors",
459
+ "single_transformer_blocks.3.attn.norm_q.weight": "model-00002-of-00004.safetensors",
460
+ "single_transformer_blocks.3.attn.norm_k.weight": "model-00002-of-00004.safetensors",
461
+ "single_transformer_blocks.3.attn.to_q.qweight": "model-00002-of-00004.safetensors",
462
+ "single_transformer_blocks.3.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
463
+ "single_transformer_blocks.3.attn.to_q.scales": "model-00002-of-00004.safetensors",
464
+ "single_transformer_blocks.3.attn.to_q.bias": "model-00002-of-00004.safetensors",
465
+ "single_transformer_blocks.3.attn.to_k.qweight": "model-00002-of-00004.safetensors",
466
+ "single_transformer_blocks.3.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
467
+ "single_transformer_blocks.3.attn.to_k.scales": "model-00002-of-00004.safetensors",
468
+ "single_transformer_blocks.3.attn.to_k.bias": "model-00002-of-00004.safetensors",
469
+ "single_transformer_blocks.3.attn.to_v.qweight": "model-00002-of-00004.safetensors",
470
+ "single_transformer_blocks.3.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
471
+ "single_transformer_blocks.3.attn.to_v.scales": "model-00002-of-00004.safetensors",
472
+ "single_transformer_blocks.3.attn.to_v.bias": "model-00002-of-00004.safetensors",
473
+ "single_transformer_blocks.4.norm.linear.qweight": "model-00002-of-00004.safetensors",
474
+ "single_transformer_blocks.4.norm.linear.qzeros": "model-00002-of-00004.safetensors",
475
+ "single_transformer_blocks.4.norm.linear.scales": "model-00002-of-00004.safetensors",
476
+ "single_transformer_blocks.4.norm.linear.bias": "model-00002-of-00004.safetensors",
477
+ "single_transformer_blocks.4.proj_mlp.qweight": "model-00002-of-00004.safetensors",
478
+ "single_transformer_blocks.4.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
479
+ "single_transformer_blocks.4.proj_mlp.scales": "model-00002-of-00004.safetensors",
480
+ "single_transformer_blocks.4.proj_mlp.bias": "model-00002-of-00004.safetensors",
481
+ "single_transformer_blocks.4.proj_out.qweight": "model-00002-of-00004.safetensors",
482
+ "single_transformer_blocks.4.proj_out.qzeros": "model-00002-of-00004.safetensors",
483
+ "single_transformer_blocks.4.proj_out.scales": "model-00002-of-00004.safetensors",
484
+ "single_transformer_blocks.4.proj_out.bias": "model-00002-of-00004.safetensors",
485
+ "single_transformer_blocks.4.attn.norm_q.weight": "model-00002-of-00004.safetensors",
486
+ "single_transformer_blocks.4.attn.norm_k.weight": "model-00002-of-00004.safetensors",
487
+ "single_transformer_blocks.4.attn.to_q.qweight": "model-00002-of-00004.safetensors",
488
+ "single_transformer_blocks.4.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
489
+ "single_transformer_blocks.4.attn.to_q.scales": "model-00002-of-00004.safetensors",
490
+ "single_transformer_blocks.4.attn.to_q.bias": "model-00002-of-00004.safetensors",
491
+ "single_transformer_blocks.4.attn.to_k.qweight": "model-00002-of-00004.safetensors",
492
+ "single_transformer_blocks.4.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
493
+ "single_transformer_blocks.4.attn.to_k.scales": "model-00002-of-00004.safetensors",
494
+ "single_transformer_blocks.4.attn.to_k.bias": "model-00002-of-00004.safetensors",
495
+ "single_transformer_blocks.4.attn.to_v.qweight": "model-00002-of-00004.safetensors",
496
+ "single_transformer_blocks.4.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
497
+ "single_transformer_blocks.4.attn.to_v.scales": "model-00002-of-00004.safetensors",
498
+ "single_transformer_blocks.4.attn.to_v.bias": "model-00002-of-00004.safetensors",
499
+ "single_transformer_blocks.5.norm.linear.qweight": "model-00002-of-00004.safetensors",
500
+ "single_transformer_blocks.5.norm.linear.qzeros": "model-00002-of-00004.safetensors",
501
+ "single_transformer_blocks.5.norm.linear.scales": "model-00002-of-00004.safetensors",
502
+ "single_transformer_blocks.5.norm.linear.bias": "model-00002-of-00004.safetensors",
503
+ "single_transformer_blocks.5.proj_mlp.qweight": "model-00002-of-00004.safetensors",
504
+ "single_transformer_blocks.5.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
505
+ "single_transformer_blocks.5.proj_mlp.scales": "model-00002-of-00004.safetensors",
506
+ "single_transformer_blocks.5.proj_mlp.bias": "model-00002-of-00004.safetensors",
507
+ "single_transformer_blocks.5.proj_out.qweight": "model-00002-of-00004.safetensors",
508
+ "single_transformer_blocks.5.proj_out.qzeros": "model-00002-of-00004.safetensors",
509
+ "single_transformer_blocks.5.proj_out.scales": "model-00002-of-00004.safetensors",
510
+ "single_transformer_blocks.5.proj_out.bias": "model-00002-of-00004.safetensors",
511
+ "single_transformer_blocks.5.attn.norm_q.weight": "model-00002-of-00004.safetensors",
512
+ "single_transformer_blocks.5.attn.norm_k.weight": "model-00002-of-00004.safetensors",
513
+ "single_transformer_blocks.5.attn.to_q.qweight": "model-00002-of-00004.safetensors",
514
+ "single_transformer_blocks.5.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
515
+ "single_transformer_blocks.5.attn.to_q.scales": "model-00002-of-00004.safetensors",
516
+ "single_transformer_blocks.5.attn.to_q.bias": "model-00002-of-00004.safetensors",
517
+ "single_transformer_blocks.5.attn.to_k.qweight": "model-00002-of-00004.safetensors",
518
+ "single_transformer_blocks.5.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
519
+ "single_transformer_blocks.5.attn.to_k.scales": "model-00002-of-00004.safetensors",
520
+ "single_transformer_blocks.5.attn.to_k.bias": "model-00002-of-00004.safetensors",
521
+ "single_transformer_blocks.5.attn.to_v.qweight": "model-00002-of-00004.safetensors",
522
+ "single_transformer_blocks.5.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
523
+ "single_transformer_blocks.5.attn.to_v.scales": "model-00002-of-00004.safetensors",
524
+ "single_transformer_blocks.5.attn.to_v.bias": "model-00002-of-00004.safetensors",
525
+ "single_transformer_blocks.6.norm.linear.qweight": "model-00002-of-00004.safetensors",
526
+ "single_transformer_blocks.6.norm.linear.qzeros": "model-00002-of-00004.safetensors",
527
+ "single_transformer_blocks.6.norm.linear.scales": "model-00002-of-00004.safetensors",
528
+ "single_transformer_blocks.6.norm.linear.bias": "model-00002-of-00004.safetensors",
529
+ "single_transformer_blocks.6.proj_mlp.qweight": "model-00002-of-00004.safetensors",
530
+ "single_transformer_blocks.6.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
531
+ "single_transformer_blocks.6.proj_mlp.scales": "model-00002-of-00004.safetensors",
532
+ "single_transformer_blocks.6.proj_mlp.bias": "model-00002-of-00004.safetensors",
533
+ "single_transformer_blocks.6.proj_out.qweight": "model-00002-of-00004.safetensors",
534
+ "single_transformer_blocks.6.proj_out.qzeros": "model-00002-of-00004.safetensors",
535
+ "single_transformer_blocks.6.proj_out.scales": "model-00002-of-00004.safetensors",
536
+ "single_transformer_blocks.6.proj_out.bias": "model-00002-of-00004.safetensors",
537
+ "single_transformer_blocks.6.attn.norm_q.weight": "model-00002-of-00004.safetensors",
538
+ "single_transformer_blocks.6.attn.norm_k.weight": "model-00002-of-00004.safetensors",
539
+ "single_transformer_blocks.6.attn.to_q.qweight": "model-00002-of-00004.safetensors",
540
+ "single_transformer_blocks.6.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
541
+ "single_transformer_blocks.6.attn.to_q.scales": "model-00002-of-00004.safetensors",
542
+ "single_transformer_blocks.6.attn.to_q.bias": "model-00002-of-00004.safetensors",
543
+ "single_transformer_blocks.6.attn.to_k.qweight": "model-00002-of-00004.safetensors",
544
+ "single_transformer_blocks.6.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
545
+ "single_transformer_blocks.6.attn.to_k.scales": "model-00002-of-00004.safetensors",
546
+ "single_transformer_blocks.6.attn.to_k.bias": "model-00002-of-00004.safetensors",
547
+ "single_transformer_blocks.6.attn.to_v.qweight": "model-00002-of-00004.safetensors",
548
+ "single_transformer_blocks.6.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
549
+ "single_transformer_blocks.6.attn.to_v.scales": "model-00002-of-00004.safetensors",
550
+ "single_transformer_blocks.6.attn.to_v.bias": "model-00002-of-00004.safetensors",
551
+ "single_transformer_blocks.7.norm.linear.qweight": "model-00002-of-00004.safetensors",
552
+ "single_transformer_blocks.7.norm.linear.qzeros": "model-00002-of-00004.safetensors",
553
+ "single_transformer_blocks.7.norm.linear.scales": "model-00002-of-00004.safetensors",
554
+ "single_transformer_blocks.7.norm.linear.bias": "model-00002-of-00004.safetensors",
555
+ "single_transformer_blocks.7.proj_mlp.qweight": "model-00002-of-00004.safetensors",
556
+ "single_transformer_blocks.7.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
557
+ "single_transformer_blocks.7.proj_mlp.scales": "model-00002-of-00004.safetensors",
558
+ "single_transformer_blocks.7.proj_mlp.bias": "model-00002-of-00004.safetensors",
559
+ "single_transformer_blocks.7.proj_out.qweight": "model-00002-of-00004.safetensors",
560
+ "single_transformer_blocks.7.proj_out.qzeros": "model-00002-of-00004.safetensors",
561
+ "single_transformer_blocks.7.proj_out.scales": "model-00002-of-00004.safetensors",
562
+ "single_transformer_blocks.7.proj_out.bias": "model-00002-of-00004.safetensors",
563
+ "single_transformer_blocks.7.attn.norm_q.weight": "model-00002-of-00004.safetensors",
564
+ "single_transformer_blocks.7.attn.norm_k.weight": "model-00002-of-00004.safetensors",
565
+ "single_transformer_blocks.7.attn.to_q.qweight": "model-00002-of-00004.safetensors",
566
+ "single_transformer_blocks.7.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
567
+ "single_transformer_blocks.7.attn.to_q.scales": "model-00002-of-00004.safetensors",
568
+ "single_transformer_blocks.7.attn.to_q.bias": "model-00002-of-00004.safetensors",
569
+ "single_transformer_blocks.7.attn.to_k.qweight": "model-00002-of-00004.safetensors",
570
+ "single_transformer_blocks.7.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
571
+ "single_transformer_blocks.7.attn.to_k.scales": "model-00002-of-00004.safetensors",
572
+ "single_transformer_blocks.7.attn.to_k.bias": "model-00002-of-00004.safetensors",
573
+ "single_transformer_blocks.7.attn.to_v.qweight": "model-00002-of-00004.safetensors",
574
+ "single_transformer_blocks.7.attn.to_v.qzeros": "model-00002-of-00004.safetensors",
575
+ "single_transformer_blocks.7.attn.to_v.scales": "model-00002-of-00004.safetensors",
576
+ "single_transformer_blocks.7.attn.to_v.bias": "model-00002-of-00004.safetensors",
577
+ "single_transformer_blocks.8.norm.linear.qweight": "model-00002-of-00004.safetensors",
578
+ "single_transformer_blocks.8.norm.linear.qzeros": "model-00002-of-00004.safetensors",
579
+ "single_transformer_blocks.8.norm.linear.scales": "model-00002-of-00004.safetensors",
580
+ "single_transformer_blocks.8.norm.linear.bias": "model-00002-of-00004.safetensors",
581
+ "single_transformer_blocks.8.proj_mlp.qweight": "model-00002-of-00004.safetensors",
582
+ "single_transformer_blocks.8.proj_mlp.qzeros": "model-00002-of-00004.safetensors",
583
+ "single_transformer_blocks.8.proj_mlp.scales": "model-00002-of-00004.safetensors",
584
+ "single_transformer_blocks.8.proj_mlp.bias": "model-00002-of-00004.safetensors",
585
+ "single_transformer_blocks.8.proj_out.qweight": "model-00002-of-00004.safetensors",
586
+ "single_transformer_blocks.8.proj_out.qzeros": "model-00002-of-00004.safetensors",
587
+ "single_transformer_blocks.8.proj_out.scales": "model-00002-of-00004.safetensors",
588
+ "single_transformer_blocks.8.proj_out.bias": "model-00002-of-00004.safetensors",
589
+ "single_transformer_blocks.8.attn.norm_q.weight": "model-00002-of-00004.safetensors",
590
+ "single_transformer_blocks.8.attn.norm_k.weight": "model-00002-of-00004.safetensors",
591
+ "single_transformer_blocks.8.attn.to_q.qweight": "model-00002-of-00004.safetensors",
592
+ "single_transformer_blocks.8.attn.to_q.qzeros": "model-00002-of-00004.safetensors",
593
+ "single_transformer_blocks.8.attn.to_q.scales": "model-00002-of-00004.safetensors",
594
+ "single_transformer_blocks.8.attn.to_q.bias": "model-00002-of-00004.safetensors",
595
+ "single_transformer_blocks.8.attn.to_k.qweight": "model-00002-of-00004.safetensors",
596
+ "single_transformer_blocks.8.attn.to_k.qzeros": "model-00002-of-00004.safetensors",
597
+ "single_transformer_blocks.8.attn.to_k.scales": "model-00002-of-00004.safetensors",
598
+ "single_transformer_blocks.8.attn.to_k.bias": "model-00002-of-00004.safetensors",
599
+ "single_transformer_blocks.8.attn.to_v.qweight": "model-00003-of-00004.safetensors",
600
+ "single_transformer_blocks.8.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
601
+ "single_transformer_blocks.8.attn.to_v.scales": "model-00003-of-00004.safetensors",
602
+ "single_transformer_blocks.8.attn.to_v.bias": "model-00003-of-00004.safetensors",
603
+ "single_transformer_blocks.9.norm.linear.qweight": "model-00003-of-00004.safetensors",
604
+ "single_transformer_blocks.9.norm.linear.qzeros": "model-00003-of-00004.safetensors",
605
+ "single_transformer_blocks.9.norm.linear.scales": "model-00003-of-00004.safetensors",
606
+ "single_transformer_blocks.9.norm.linear.bias": "model-00003-of-00004.safetensors",
607
+ "single_transformer_blocks.9.proj_mlp.qweight": "model-00003-of-00004.safetensors",
608
+ "single_transformer_blocks.9.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
609
+ "single_transformer_blocks.9.proj_mlp.scales": "model-00003-of-00004.safetensors",
610
+ "single_transformer_blocks.9.proj_mlp.bias": "model-00003-of-00004.safetensors",
611
+ "single_transformer_blocks.9.proj_out.qweight": "model-00003-of-00004.safetensors",
612
+ "single_transformer_blocks.9.proj_out.qzeros": "model-00003-of-00004.safetensors",
613
+ "single_transformer_blocks.9.proj_out.scales": "model-00003-of-00004.safetensors",
614
+ "single_transformer_blocks.9.proj_out.bias": "model-00003-of-00004.safetensors",
615
+ "single_transformer_blocks.9.attn.norm_q.weight": "model-00003-of-00004.safetensors",
616
+ "single_transformer_blocks.9.attn.norm_k.weight": "model-00003-of-00004.safetensors",
617
+ "single_transformer_blocks.9.attn.to_q.qweight": "model-00003-of-00004.safetensors",
618
+ "single_transformer_blocks.9.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
619
+ "single_transformer_blocks.9.attn.to_q.scales": "model-00003-of-00004.safetensors",
620
+ "single_transformer_blocks.9.attn.to_q.bias": "model-00003-of-00004.safetensors",
621
+ "single_transformer_blocks.9.attn.to_k.qweight": "model-00003-of-00004.safetensors",
622
+ "single_transformer_blocks.9.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
623
+ "single_transformer_blocks.9.attn.to_k.scales": "model-00003-of-00004.safetensors",
624
+ "single_transformer_blocks.9.attn.to_k.bias": "model-00003-of-00004.safetensors",
625
+ "single_transformer_blocks.9.attn.to_v.qweight": "model-00003-of-00004.safetensors",
626
+ "single_transformer_blocks.9.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
627
+ "single_transformer_blocks.9.attn.to_v.scales": "model-00003-of-00004.safetensors",
628
+ "single_transformer_blocks.9.attn.to_v.bias": "model-00003-of-00004.safetensors",
629
+ "single_transformer_blocks.10.norm.linear.qweight": "model-00003-of-00004.safetensors",
630
+ "single_transformer_blocks.10.norm.linear.qzeros": "model-00003-of-00004.safetensors",
631
+ "single_transformer_blocks.10.norm.linear.scales": "model-00003-of-00004.safetensors",
632
+ "single_transformer_blocks.10.norm.linear.bias": "model-00003-of-00004.safetensors",
633
+ "single_transformer_blocks.10.proj_mlp.qweight": "model-00003-of-00004.safetensors",
634
+ "single_transformer_blocks.10.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
635
+ "single_transformer_blocks.10.proj_mlp.scales": "model-00003-of-00004.safetensors",
636
+ "single_transformer_blocks.10.proj_mlp.bias": "model-00003-of-00004.safetensors",
637
+ "single_transformer_blocks.10.proj_out.qweight": "model-00003-of-00004.safetensors",
638
+ "single_transformer_blocks.10.proj_out.qzeros": "model-00003-of-00004.safetensors",
639
+ "single_transformer_blocks.10.proj_out.scales": "model-00003-of-00004.safetensors",
640
+ "single_transformer_blocks.10.proj_out.bias": "model-00003-of-00004.safetensors",
641
+ "single_transformer_blocks.10.attn.norm_q.weight": "model-00003-of-00004.safetensors",
642
+ "single_transformer_blocks.10.attn.norm_k.weight": "model-00003-of-00004.safetensors",
643
+ "single_transformer_blocks.10.attn.to_q.qweight": "model-00003-of-00004.safetensors",
644
+ "single_transformer_blocks.10.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
645
+ "single_transformer_blocks.10.attn.to_q.scales": "model-00003-of-00004.safetensors",
646
+ "single_transformer_blocks.10.attn.to_q.bias": "model-00003-of-00004.safetensors",
647
+ "single_transformer_blocks.10.attn.to_k.qweight": "model-00003-of-00004.safetensors",
648
+ "single_transformer_blocks.10.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
649
+ "single_transformer_blocks.10.attn.to_k.scales": "model-00003-of-00004.safetensors",
650
+ "single_transformer_blocks.10.attn.to_k.bias": "model-00003-of-00004.safetensors",
651
+ "single_transformer_blocks.10.attn.to_v.qweight": "model-00003-of-00004.safetensors",
652
+ "single_transformer_blocks.10.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
653
+ "single_transformer_blocks.10.attn.to_v.scales": "model-00003-of-00004.safetensors",
654
+ "single_transformer_blocks.10.attn.to_v.bias": "model-00003-of-00004.safetensors",
655
+ "single_transformer_blocks.11.norm.linear.qweight": "model-00003-of-00004.safetensors",
656
+ "single_transformer_blocks.11.norm.linear.qzeros": "model-00003-of-00004.safetensors",
657
+ "single_transformer_blocks.11.norm.linear.scales": "model-00003-of-00004.safetensors",
658
+ "single_transformer_blocks.11.norm.linear.bias": "model-00003-of-00004.safetensors",
659
+ "single_transformer_blocks.11.proj_mlp.qweight": "model-00003-of-00004.safetensors",
660
+ "single_transformer_blocks.11.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
661
+ "single_transformer_blocks.11.proj_mlp.scales": "model-00003-of-00004.safetensors",
662
+ "single_transformer_blocks.11.proj_mlp.bias": "model-00003-of-00004.safetensors",
663
+ "single_transformer_blocks.11.proj_out.qweight": "model-00003-of-00004.safetensors",
664
+ "single_transformer_blocks.11.proj_out.qzeros": "model-00003-of-00004.safetensors",
665
+ "single_transformer_blocks.11.proj_out.scales": "model-00003-of-00004.safetensors",
666
+ "single_transformer_blocks.11.proj_out.bias": "model-00003-of-00004.safetensors",
667
+ "single_transformer_blocks.11.attn.norm_q.weight": "model-00003-of-00004.safetensors",
668
+ "single_transformer_blocks.11.attn.norm_k.weight": "model-00003-of-00004.safetensors",
669
+ "single_transformer_blocks.11.attn.to_q.qweight": "model-00003-of-00004.safetensors",
670
+ "single_transformer_blocks.11.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
671
+ "single_transformer_blocks.11.attn.to_q.scales": "model-00003-of-00004.safetensors",
672
+ "single_transformer_blocks.11.attn.to_q.bias": "model-00003-of-00004.safetensors",
673
+ "single_transformer_blocks.11.attn.to_k.qweight": "model-00003-of-00004.safetensors",
674
+ "single_transformer_blocks.11.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
675
+ "single_transformer_blocks.11.attn.to_k.scales": "model-00003-of-00004.safetensors",
676
+ "single_transformer_blocks.11.attn.to_k.bias": "model-00003-of-00004.safetensors",
677
+ "single_transformer_blocks.11.attn.to_v.qweight": "model-00003-of-00004.safetensors",
678
+ "single_transformer_blocks.11.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
679
+ "single_transformer_blocks.11.attn.to_v.scales": "model-00003-of-00004.safetensors",
680
+ "single_transformer_blocks.11.attn.to_v.bias": "model-00003-of-00004.safetensors",
681
+ "single_transformer_blocks.12.norm.linear.qweight": "model-00003-of-00004.safetensors",
682
+ "single_transformer_blocks.12.norm.linear.qzeros": "model-00003-of-00004.safetensors",
683
+ "single_transformer_blocks.12.norm.linear.scales": "model-00003-of-00004.safetensors",
684
+ "single_transformer_blocks.12.norm.linear.bias": "model-00003-of-00004.safetensors",
685
+ "single_transformer_blocks.12.proj_mlp.qweight": "model-00003-of-00004.safetensors",
686
+ "single_transformer_blocks.12.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
687
+ "single_transformer_blocks.12.proj_mlp.scales": "model-00003-of-00004.safetensors",
688
+ "single_transformer_blocks.12.proj_mlp.bias": "model-00003-of-00004.safetensors",
689
+ "single_transformer_blocks.12.proj_out.qweight": "model-00003-of-00004.safetensors",
690
+ "single_transformer_blocks.12.proj_out.qzeros": "model-00003-of-00004.safetensors",
691
+ "single_transformer_blocks.12.proj_out.scales": "model-00003-of-00004.safetensors",
692
+ "single_transformer_blocks.12.proj_out.bias": "model-00003-of-00004.safetensors",
693
+ "single_transformer_blocks.12.attn.norm_q.weight": "model-00003-of-00004.safetensors",
694
+ "single_transformer_blocks.12.attn.norm_k.weight": "model-00003-of-00004.safetensors",
695
+ "single_transformer_blocks.12.attn.to_q.qweight": "model-00003-of-00004.safetensors",
696
+ "single_transformer_blocks.12.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
697
+ "single_transformer_blocks.12.attn.to_q.scales": "model-00003-of-00004.safetensors",
698
+ "single_transformer_blocks.12.attn.to_q.bias": "model-00003-of-00004.safetensors",
699
+ "single_transformer_blocks.12.attn.to_k.qweight": "model-00003-of-00004.safetensors",
700
+ "single_transformer_blocks.12.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
701
+ "single_transformer_blocks.12.attn.to_k.scales": "model-00003-of-00004.safetensors",
702
+ "single_transformer_blocks.12.attn.to_k.bias": "model-00003-of-00004.safetensors",
703
+ "single_transformer_blocks.12.attn.to_v.qweight": "model-00003-of-00004.safetensors",
704
+ "single_transformer_blocks.12.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
705
+ "single_transformer_blocks.12.attn.to_v.scales": "model-00003-of-00004.safetensors",
706
+ "single_transformer_blocks.12.attn.to_v.bias": "model-00003-of-00004.safetensors",
707
+ "single_transformer_blocks.13.norm.linear.qweight": "model-00003-of-00004.safetensors",
708
+ "single_transformer_blocks.13.norm.linear.qzeros": "model-00003-of-00004.safetensors",
709
+ "single_transformer_blocks.13.norm.linear.scales": "model-00003-of-00004.safetensors",
710
+ "single_transformer_blocks.13.norm.linear.bias": "model-00003-of-00004.safetensors",
711
+ "single_transformer_blocks.13.proj_mlp.qweight": "model-00003-of-00004.safetensors",
712
+ "single_transformer_blocks.13.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
713
+ "single_transformer_blocks.13.proj_mlp.scales": "model-00003-of-00004.safetensors",
714
+ "single_transformer_blocks.13.proj_mlp.bias": "model-00003-of-00004.safetensors",
715
+ "single_transformer_blocks.13.proj_out.qweight": "model-00003-of-00004.safetensors",
716
+ "single_transformer_blocks.13.proj_out.qzeros": "model-00003-of-00004.safetensors",
717
+ "single_transformer_blocks.13.proj_out.scales": "model-00003-of-00004.safetensors",
718
+ "single_transformer_blocks.13.proj_out.bias": "model-00003-of-00004.safetensors",
719
+ "single_transformer_blocks.13.attn.norm_q.weight": "model-00003-of-00004.safetensors",
720
+ "single_transformer_blocks.13.attn.norm_k.weight": "model-00003-of-00004.safetensors",
721
+ "single_transformer_blocks.13.attn.to_q.qweight": "model-00003-of-00004.safetensors",
722
+ "single_transformer_blocks.13.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
723
+ "single_transformer_blocks.13.attn.to_q.scales": "model-00003-of-00004.safetensors",
724
+ "single_transformer_blocks.13.attn.to_q.bias": "model-00003-of-00004.safetensors",
725
+ "single_transformer_blocks.13.attn.to_k.qweight": "model-00003-of-00004.safetensors",
726
+ "single_transformer_blocks.13.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
727
+ "single_transformer_blocks.13.attn.to_k.scales": "model-00003-of-00004.safetensors",
728
+ "single_transformer_blocks.13.attn.to_k.bias": "model-00003-of-00004.safetensors",
729
+ "single_transformer_blocks.13.attn.to_v.qweight": "model-00003-of-00004.safetensors",
730
+ "single_transformer_blocks.13.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
731
+ "single_transformer_blocks.13.attn.to_v.scales": "model-00003-of-00004.safetensors",
732
+ "single_transformer_blocks.13.attn.to_v.bias": "model-00003-of-00004.safetensors",
733
+ "single_transformer_blocks.14.norm.linear.qweight": "model-00003-of-00004.safetensors",
734
+ "single_transformer_blocks.14.norm.linear.qzeros": "model-00003-of-00004.safetensors",
735
+ "single_transformer_blocks.14.norm.linear.scales": "model-00003-of-00004.safetensors",
736
+ "single_transformer_blocks.14.norm.linear.bias": "model-00003-of-00004.safetensors",
737
+ "single_transformer_blocks.14.proj_mlp.qweight": "model-00003-of-00004.safetensors",
738
+ "single_transformer_blocks.14.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
739
+ "single_transformer_blocks.14.proj_mlp.scales": "model-00003-of-00004.safetensors",
740
+ "single_transformer_blocks.14.proj_mlp.bias": "model-00003-of-00004.safetensors",
741
+ "single_transformer_blocks.14.proj_out.qweight": "model-00003-of-00004.safetensors",
742
+ "single_transformer_blocks.14.proj_out.qzeros": "model-00003-of-00004.safetensors",
743
+ "single_transformer_blocks.14.proj_out.scales": "model-00003-of-00004.safetensors",
744
+ "single_transformer_blocks.14.proj_out.bias": "model-00003-of-00004.safetensors",
745
+ "single_transformer_blocks.14.attn.norm_q.weight": "model-00003-of-00004.safetensors",
746
+ "single_transformer_blocks.14.attn.norm_k.weight": "model-00003-of-00004.safetensors",
747
+ "single_transformer_blocks.14.attn.to_q.qweight": "model-00003-of-00004.safetensors",
748
+ "single_transformer_blocks.14.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
749
+ "single_transformer_blocks.14.attn.to_q.scales": "model-00003-of-00004.safetensors",
750
+ "single_transformer_blocks.14.attn.to_q.bias": "model-00003-of-00004.safetensors",
751
+ "single_transformer_blocks.14.attn.to_k.qweight": "model-00003-of-00004.safetensors",
752
+ "single_transformer_blocks.14.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
753
+ "single_transformer_blocks.14.attn.to_k.scales": "model-00003-of-00004.safetensors",
754
+ "single_transformer_blocks.14.attn.to_k.bias": "model-00003-of-00004.safetensors",
755
+ "single_transformer_blocks.14.attn.to_v.qweight": "model-00003-of-00004.safetensors",
756
+ "single_transformer_blocks.14.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
757
+ "single_transformer_blocks.14.attn.to_v.scales": "model-00003-of-00004.safetensors",
758
+ "single_transformer_blocks.14.attn.to_v.bias": "model-00003-of-00004.safetensors",
759
+ "single_transformer_blocks.15.norm.linear.qweight": "model-00003-of-00004.safetensors",
760
+ "single_transformer_blocks.15.norm.linear.qzeros": "model-00003-of-00004.safetensors",
761
+ "single_transformer_blocks.15.norm.linear.scales": "model-00003-of-00004.safetensors",
762
+ "single_transformer_blocks.15.norm.linear.bias": "model-00003-of-00004.safetensors",
763
+ "single_transformer_blocks.15.proj_mlp.qweight": "model-00003-of-00004.safetensors",
764
+ "single_transformer_blocks.15.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
765
+ "single_transformer_blocks.15.proj_mlp.scales": "model-00003-of-00004.safetensors",
766
+ "single_transformer_blocks.15.proj_mlp.bias": "model-00003-of-00004.safetensors",
767
+ "single_transformer_blocks.15.proj_out.qweight": "model-00003-of-00004.safetensors",
768
+ "single_transformer_blocks.15.proj_out.qzeros": "model-00003-of-00004.safetensors",
769
+ "single_transformer_blocks.15.proj_out.scales": "model-00003-of-00004.safetensors",
770
+ "single_transformer_blocks.15.proj_out.bias": "model-00003-of-00004.safetensors",
771
+ "single_transformer_blocks.15.attn.norm_q.weight": "model-00003-of-00004.safetensors",
772
+ "single_transformer_blocks.15.attn.norm_k.weight": "model-00003-of-00004.safetensors",
773
+ "single_transformer_blocks.15.attn.to_q.qweight": "model-00003-of-00004.safetensors",
774
+ "single_transformer_blocks.15.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
775
+ "single_transformer_blocks.15.attn.to_q.scales": "model-00003-of-00004.safetensors",
776
+ "single_transformer_blocks.15.attn.to_q.bias": "model-00003-of-00004.safetensors",
777
+ "single_transformer_blocks.15.attn.to_k.qweight": "model-00003-of-00004.safetensors",
778
+ "single_transformer_blocks.15.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
779
+ "single_transformer_blocks.15.attn.to_k.scales": "model-00003-of-00004.safetensors",
780
+ "single_transformer_blocks.15.attn.to_k.bias": "model-00003-of-00004.safetensors",
781
+ "single_transformer_blocks.15.attn.to_v.qweight": "model-00003-of-00004.safetensors",
782
+ "single_transformer_blocks.15.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
783
+ "single_transformer_blocks.15.attn.to_v.scales": "model-00003-of-00004.safetensors",
784
+ "single_transformer_blocks.15.attn.to_v.bias": "model-00003-of-00004.safetensors",
785
+ "single_transformer_blocks.16.norm.linear.qweight": "model-00003-of-00004.safetensors",
786
+ "single_transformer_blocks.16.norm.linear.qzeros": "model-00003-of-00004.safetensors",
787
+ "single_transformer_blocks.16.norm.linear.scales": "model-00003-of-00004.safetensors",
788
+ "single_transformer_blocks.16.norm.linear.bias": "model-00003-of-00004.safetensors",
789
+ "single_transformer_blocks.16.proj_mlp.qweight": "model-00003-of-00004.safetensors",
790
+ "single_transformer_blocks.16.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
791
+ "single_transformer_blocks.16.proj_mlp.scales": "model-00003-of-00004.safetensors",
792
+ "single_transformer_blocks.16.proj_mlp.bias": "model-00003-of-00004.safetensors",
793
+ "single_transformer_blocks.16.proj_out.qweight": "model-00003-of-00004.safetensors",
794
+ "single_transformer_blocks.16.proj_out.qzeros": "model-00003-of-00004.safetensors",
795
+ "single_transformer_blocks.16.proj_out.scales": "model-00003-of-00004.safetensors",
796
+ "single_transformer_blocks.16.proj_out.bias": "model-00003-of-00004.safetensors",
797
+ "single_transformer_blocks.16.attn.norm_q.weight": "model-00003-of-00004.safetensors",
798
+ "single_transformer_blocks.16.attn.norm_k.weight": "model-00003-of-00004.safetensors",
799
+ "single_transformer_blocks.16.attn.to_q.qweight": "model-00003-of-00004.safetensors",
800
+ "single_transformer_blocks.16.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
801
+ "single_transformer_blocks.16.attn.to_q.scales": "model-00003-of-00004.safetensors",
802
+ "single_transformer_blocks.16.attn.to_q.bias": "model-00003-of-00004.safetensors",
803
+ "single_transformer_blocks.16.attn.to_k.qweight": "model-00003-of-00004.safetensors",
804
+ "single_transformer_blocks.16.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
805
+ "single_transformer_blocks.16.attn.to_k.scales": "model-00003-of-00004.safetensors",
806
+ "single_transformer_blocks.16.attn.to_k.bias": "model-00003-of-00004.safetensors",
807
+ "single_transformer_blocks.16.attn.to_v.qweight": "model-00003-of-00004.safetensors",
808
+ "single_transformer_blocks.16.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
809
+ "single_transformer_blocks.16.attn.to_v.scales": "model-00003-of-00004.safetensors",
810
+ "single_transformer_blocks.16.attn.to_v.bias": "model-00003-of-00004.safetensors",
811
+ "single_transformer_blocks.17.norm.linear.qweight": "model-00003-of-00004.safetensors",
812
+ "single_transformer_blocks.17.norm.linear.qzeros": "model-00003-of-00004.safetensors",
813
+ "single_transformer_blocks.17.norm.linear.scales": "model-00003-of-00004.safetensors",
814
+ "single_transformer_blocks.17.norm.linear.bias": "model-00003-of-00004.safetensors",
815
+ "single_transformer_blocks.17.proj_mlp.qweight": "model-00003-of-00004.safetensors",
816
+ "single_transformer_blocks.17.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
817
+ "single_transformer_blocks.17.proj_mlp.scales": "model-00003-of-00004.safetensors",
818
+ "single_transformer_blocks.17.proj_mlp.bias": "model-00003-of-00004.safetensors",
819
+ "single_transformer_blocks.17.proj_out.qweight": "model-00003-of-00004.safetensors",
820
+ "single_transformer_blocks.17.proj_out.qzeros": "model-00003-of-00004.safetensors",
821
+ "single_transformer_blocks.17.proj_out.scales": "model-00003-of-00004.safetensors",
822
+ "single_transformer_blocks.17.proj_out.bias": "model-00003-of-00004.safetensors",
823
+ "single_transformer_blocks.17.attn.norm_q.weight": "model-00003-of-00004.safetensors",
824
+ "single_transformer_blocks.17.attn.norm_k.weight": "model-00003-of-00004.safetensors",
825
+ "single_transformer_blocks.17.attn.to_q.qweight": "model-00003-of-00004.safetensors",
826
+ "single_transformer_blocks.17.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
827
+ "single_transformer_blocks.17.attn.to_q.scales": "model-00003-of-00004.safetensors",
828
+ "single_transformer_blocks.17.attn.to_q.bias": "model-00003-of-00004.safetensors",
829
+ "single_transformer_blocks.17.attn.to_k.qweight": "model-00003-of-00004.safetensors",
830
+ "single_transformer_blocks.17.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
831
+ "single_transformer_blocks.17.attn.to_k.scales": "model-00003-of-00004.safetensors",
832
+ "single_transformer_blocks.17.attn.to_k.bias": "model-00003-of-00004.safetensors",
833
+ "single_transformer_blocks.17.attn.to_v.qweight": "model-00003-of-00004.safetensors",
834
+ "single_transformer_blocks.17.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
835
+ "single_transformer_blocks.17.attn.to_v.scales": "model-00003-of-00004.safetensors",
836
+ "single_transformer_blocks.17.attn.to_v.bias": "model-00003-of-00004.safetensors",
837
+ "single_transformer_blocks.18.norm.linear.qweight": "model-00003-of-00004.safetensors",
838
+ "single_transformer_blocks.18.norm.linear.qzeros": "model-00003-of-00004.safetensors",
839
+ "single_transformer_blocks.18.norm.linear.scales": "model-00003-of-00004.safetensors",
840
+ "single_transformer_blocks.18.norm.linear.bias": "model-00003-of-00004.safetensors",
841
+ "single_transformer_blocks.18.proj_mlp.qweight": "model-00003-of-00004.safetensors",
842
+ "single_transformer_blocks.18.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
843
+ "single_transformer_blocks.18.proj_mlp.scales": "model-00003-of-00004.safetensors",
844
+ "single_transformer_blocks.18.proj_mlp.bias": "model-00003-of-00004.safetensors",
845
+ "single_transformer_blocks.18.proj_out.qweight": "model-00003-of-00004.safetensors",
846
+ "single_transformer_blocks.18.proj_out.qzeros": "model-00003-of-00004.safetensors",
847
+ "single_transformer_blocks.18.proj_out.scales": "model-00003-of-00004.safetensors",
848
+ "single_transformer_blocks.18.proj_out.bias": "model-00003-of-00004.safetensors",
849
+ "single_transformer_blocks.18.attn.norm_q.weight": "model-00003-of-00004.safetensors",
850
+ "single_transformer_blocks.18.attn.norm_k.weight": "model-00003-of-00004.safetensors",
851
+ "single_transformer_blocks.18.attn.to_q.qweight": "model-00003-of-00004.safetensors",
852
+ "single_transformer_blocks.18.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
853
+ "single_transformer_blocks.18.attn.to_q.scales": "model-00003-of-00004.safetensors",
854
+ "single_transformer_blocks.18.attn.to_q.bias": "model-00003-of-00004.safetensors",
855
+ "single_transformer_blocks.18.attn.to_k.qweight": "model-00003-of-00004.safetensors",
856
+ "single_transformer_blocks.18.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
857
+ "single_transformer_blocks.18.attn.to_k.scales": "model-00003-of-00004.safetensors",
858
+ "single_transformer_blocks.18.attn.to_k.bias": "model-00003-of-00004.safetensors",
859
+ "single_transformer_blocks.18.attn.to_v.qweight": "model-00003-of-00004.safetensors",
860
+ "single_transformer_blocks.18.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
861
+ "single_transformer_blocks.18.attn.to_v.scales": "model-00003-of-00004.safetensors",
862
+ "single_transformer_blocks.18.attn.to_v.bias": "model-00003-of-00004.safetensors",
863
+ "single_transformer_blocks.19.norm.linear.qweight": "model-00003-of-00004.safetensors",
864
+ "single_transformer_blocks.19.norm.linear.qzeros": "model-00003-of-00004.safetensors",
865
+ "single_transformer_blocks.19.norm.linear.scales": "model-00003-of-00004.safetensors",
866
+ "single_transformer_blocks.19.norm.linear.bias": "model-00003-of-00004.safetensors",
867
+ "single_transformer_blocks.19.proj_mlp.qweight": "model-00003-of-00004.safetensors",
868
+ "single_transformer_blocks.19.proj_mlp.qzeros": "model-00003-of-00004.safetensors",
869
+ "single_transformer_blocks.19.proj_mlp.scales": "model-00003-of-00004.safetensors",
870
+ "single_transformer_blocks.19.proj_mlp.bias": "model-00003-of-00004.safetensors",
871
+ "single_transformer_blocks.19.proj_out.qweight": "model-00003-of-00004.safetensors",
872
+ "single_transformer_blocks.19.proj_out.qzeros": "model-00003-of-00004.safetensors",
873
+ "single_transformer_blocks.19.proj_out.scales": "model-00003-of-00004.safetensors",
874
+ "single_transformer_blocks.19.proj_out.bias": "model-00003-of-00004.safetensors",
875
+ "single_transformer_blocks.19.attn.norm_q.weight": "model-00003-of-00004.safetensors",
876
+ "single_transformer_blocks.19.attn.norm_k.weight": "model-00003-of-00004.safetensors",
877
+ "single_transformer_blocks.19.attn.to_q.qweight": "model-00003-of-00004.safetensors",
878
+ "single_transformer_blocks.19.attn.to_q.qzeros": "model-00003-of-00004.safetensors",
879
+ "single_transformer_blocks.19.attn.to_q.scales": "model-00003-of-00004.safetensors",
880
+ "single_transformer_blocks.19.attn.to_q.bias": "model-00003-of-00004.safetensors",
881
+ "single_transformer_blocks.19.attn.to_k.qweight": "model-00003-of-00004.safetensors",
882
+ "single_transformer_blocks.19.attn.to_k.qzeros": "model-00003-of-00004.safetensors",
883
+ "single_transformer_blocks.19.attn.to_k.scales": "model-00003-of-00004.safetensors",
884
+ "single_transformer_blocks.19.attn.to_k.bias": "model-00003-of-00004.safetensors",
885
+ "single_transformer_blocks.19.attn.to_v.qweight": "model-00003-of-00004.safetensors",
886
+ "single_transformer_blocks.19.attn.to_v.qzeros": "model-00003-of-00004.safetensors",
887
+ "single_transformer_blocks.19.attn.to_v.scales": "model-00003-of-00004.safetensors",
888
+ "single_transformer_blocks.19.attn.to_v.bias": "model-00003-of-00004.safetensors",
889
+ "single_transformer_blocks.20.norm.linear.qweight": "model-00003-of-00004.safetensors",
890
+ "single_transformer_blocks.20.norm.linear.qzeros": "model-00003-of-00004.safetensors",
891
+ "single_transformer_blocks.20.norm.linear.scales": "model-00003-of-00004.safetensors",
892
+ "single_transformer_blocks.20.norm.linear.bias": "model-00003-of-00004.safetensors",
893
+ "single_transformer_blocks.20.proj_mlp.qweight": "model-00004-of-00004.safetensors",
894
+ "single_transformer_blocks.20.proj_mlp.qzeros": "model-00004-of-00004.safetensors",
895
+ "single_transformer_blocks.20.proj_mlp.scales": "model-00004-of-00004.safetensors",
896
+ "single_transformer_blocks.20.proj_mlp.bias": "model-00004-of-00004.safetensors",
897
+ "single_transformer_blocks.20.proj_out.qweight": "model-00004-of-00004.safetensors",
898
+ "single_transformer_blocks.20.proj_out.qzeros": "model-00004-of-00004.safetensors",
899
+ "single_transformer_blocks.20.proj_out.scales": "model-00004-of-00004.safetensors",
900
+ "single_transformer_blocks.20.proj_out.bias": "model-00004-of-00004.safetensors",
901
+ "single_transformer_blocks.20.attn.norm_q.weight": "model-00004-of-00004.safetensors",
902
+ "single_transformer_blocks.20.attn.norm_k.weight": "model-00004-of-00004.safetensors",
903
+ "single_transformer_blocks.20.attn.to_q.qweight": "model-00004-of-00004.safetensors",
904
+ "single_transformer_blocks.20.attn.to_q.qzeros": "model-00004-of-00004.safetensors",
905
+ "single_transformer_blocks.20.attn.to_q.scales": "model-00004-of-00004.safetensors",
906
+ "single_transformer_blocks.20.attn.to_q.bias": "model-00004-of-00004.safetensors",
907
+ "single_transformer_blocks.20.attn.to_k.qweight": "model-00004-of-00004.safetensors",
908
+ "single_transformer_blocks.20.attn.to_k.qzeros": "model-00004-of-00004.safetensors",
909
+ "single_transformer_blocks.20.attn.to_k.scales": "model-00004-of-00004.safetensors",
910
+ "single_transformer_blocks.20.attn.to_k.bias": "model-00004-of-00004.safetensors",
911
+ "single_transformer_blocks.20.attn.to_v.qweight": "model-00004-of-00004.safetensors",
912
+ "single_transformer_blocks.20.attn.to_v.qzeros": "model-00004-of-00004.safetensors",
913
+ "single_transformer_blocks.20.attn.to_v.scales": "model-00004-of-00004.safetensors",
914
+ "single_transformer_blocks.20.attn.to_v.bias": "model-00004-of-00004.safetensors",
915
+ "single_transformer_blocks.21.norm.linear.qweight": "model-00004-of-00004.safetensors",
916
+ "single_transformer_blocks.21.norm.linear.qzeros": "model-00004-of-00004.safetensors",
917
+ "single_transformer_blocks.21.norm.linear.scales": "model-00004-of-00004.safetensors",
918
+ "single_transformer_blocks.21.norm.linear.bias": "model-00004-of-00004.safetensors",
919
+ "single_transformer_blocks.21.proj_mlp.qweight": "model-00004-of-00004.safetensors",
920
+ "single_transformer_blocks.21.proj_mlp.qzeros": "model-00004-of-00004.safetensors",
921
+ "single_transformer_blocks.21.proj_mlp.scales": "model-00004-of-00004.safetensors",
922
+ "single_transformer_blocks.21.proj_mlp.bias": "model-00004-of-00004.safetensors",
923
+ "single_transformer_blocks.21.proj_out.qweight": "model-00004-of-00004.safetensors",
924
+ "single_transformer_blocks.21.proj_out.qzeros": "model-00004-of-00004.safetensors",
925
+ "single_transformer_blocks.21.proj_out.scales": "model-00004-of-00004.safetensors",
926
+ "single_transformer_blocks.21.proj_out.bias": "model-00004-of-00004.safetensors",
927
+ "single_transformer_blocks.21.attn.norm_q.weight": "model-00004-of-00004.safetensors",
928
+ "single_transformer_blocks.21.attn.norm_k.weight": "model-00004-of-00004.safetensors",
929
+ "single_transformer_blocks.21.attn.to_q.qweight": "model-00004-of-00004.safetensors",
930
+ "single_transformer_blocks.21.attn.to_q.qzeros": "model-00004-of-00004.safetensors",
931
+ "single_transformer_blocks.21.attn.to_q.scales": "model-00004-of-00004.safetensors",
932
+ "single_transformer_blocks.21.attn.to_q.bias": "model-00004-of-00004.safetensors",
933
+ "single_transformer_blocks.21.attn.to_k.qweight": "model-00004-of-00004.safetensors",
934
+ "single_transformer_blocks.21.attn.to_k.qzeros": "model-00004-of-00004.safetensors",
935
+ "single_transformer_blocks.21.attn.to_k.scales": "model-00004-of-00004.safetensors",
936
+ "single_transformer_blocks.21.attn.to_k.bias": "model-00004-of-00004.safetensors",
937
+ "single_transformer_blocks.21.attn.to_v.qweight": "model-00004-of-00004.safetensors",
938
+ "single_transformer_blocks.21.attn.to_v.qzeros": "model-00004-of-00004.safetensors",
939
+ "single_transformer_blocks.21.attn.to_v.scales": "model-00004-of-00004.safetensors",
940
+ "single_transformer_blocks.21.attn.to_v.bias": "model-00004-of-00004.safetensors",
941
+ "single_transformer_blocks.22.norm.linear.qweight": "model-00004-of-00004.safetensors",
942
+ "single_transformer_blocks.22.norm.linear.qzeros": "model-00004-of-00004.safetensors",
943
+ "single_transformer_blocks.22.norm.linear.scales": "model-00004-of-00004.safetensors",
944
+ "single_transformer_blocks.22.norm.linear.bias": "model-00004-of-00004.safetensors",
945
+ "single_transformer_blocks.22.proj_mlp.qweight": "model-00004-of-00004.safetensors",
946
+ "single_transformer_blocks.22.proj_mlp.qzeros": "model-00004-of-00004.safetensors",
947
+ "single_transformer_blocks.22.proj_mlp.scales": "model-00004-of-00004.safetensors",
948
+ "single_transformer_blocks.22.proj_mlp.bias": "model-00004-of-00004.safetensors",
949
+ "single_transformer_blocks.22.proj_out.qweight": "model-00004-of-00004.safetensors",
950
+ "single_transformer_blocks.22.proj_out.qzeros": "model-00004-of-00004.safetensors",
951
+ "single_transformer_blocks.22.proj_out.scales": "model-00004-of-00004.safetensors",
952
+ "single_transformer_blocks.22.proj_out.bias": "model-00004-of-00004.safetensors",
953
+ "single_transformer_blocks.22.attn.norm_q.weight": "model-00004-of-00004.safetensors",
954
+ "single_transformer_blocks.22.attn.norm_k.weight": "model-00004-of-00004.safetensors",
955
+ "single_transformer_blocks.22.attn.to_q.qweight": "model-00004-of-00004.safetensors",
956
+ "single_transformer_blocks.22.attn.to_q.qzeros": "model-00004-of-00004.safetensors",
957
+ "single_transformer_blocks.22.attn.to_q.scales": "model-00004-of-00004.safetensors",
958
+ "single_transformer_blocks.22.attn.to_q.bias": "model-00004-of-00004.safetensors",
959
+ "single_transformer_blocks.22.attn.to_k.qweight": "model-00004-of-00004.safetensors",
960
+ "single_transformer_blocks.22.attn.to_k.qzeros": "model-00004-of-00004.safetensors",
961
+ "single_transformer_blocks.22.attn.to_k.scales": "model-00004-of-00004.safetensors",
962
+ "single_transformer_blocks.22.attn.to_k.bias": "model-00004-of-00004.safetensors",
963
+ "single_transformer_blocks.22.attn.to_v.qweight": "model-00004-of-00004.safetensors",
964
+ "single_transformer_blocks.22.attn.to_v.qzeros": "model-00004-of-00004.safetensors",
965
+ "single_transformer_blocks.22.attn.to_v.scales": "model-00004-of-00004.safetensors",
966
+ "single_transformer_blocks.22.attn.to_v.bias": "model-00004-of-00004.safetensors",
967
+ "single_transformer_blocks.23.norm.linear.qweight": "model-00004-of-00004.safetensors",
968
+ "single_transformer_blocks.23.norm.linear.qzeros": "model-00004-of-00004.safetensors",
969
+ "single_transformer_blocks.23.norm.linear.scales": "model-00004-of-00004.safetensors",
970
+ "single_transformer_blocks.23.norm.linear.bias": "model-00004-of-00004.safetensors",
971
+ "single_transformer_blocks.23.proj_mlp.qweight": "model-00004-of-00004.safetensors",
972
+ "single_transformer_blocks.23.proj_mlp.qzeros": "model-00004-of-00004.safetensors",
973
+ "single_transformer_blocks.23.proj_mlp.scales": "model-00004-of-00004.safetensors",
974
+ "single_transformer_blocks.23.proj_mlp.bias": "model-00004-of-00004.safetensors",
975
+ "single_transformer_blocks.23.proj_out.qweight": "model-00004-of-00004.safetensors",
976
+ "single_transformer_blocks.23.proj_out.qzeros": "model-00004-of-00004.safetensors",
977
+ "single_transformer_blocks.23.proj_out.scales": "model-00004-of-00004.safetensors",
978
+ "single_transformer_blocks.23.proj_out.bias": "model-00004-of-00004.safetensors",
979
+ "single_transformer_blocks.23.attn.norm_q.weight": "model-00004-of-00004.safetensors",
980
+ "single_transformer_blocks.23.attn.norm_k.weight": "model-00004-of-00004.safetensors",
981
+ "single_transformer_blocks.23.attn.to_q.qweight": "model-00004-of-00004.safetensors",
982
+ "single_transformer_blocks.23.attn.to_q.qzeros": "model-00004-of-00004.safetensors",
983
+ "single_transformer_blocks.23.attn.to_q.scales": "model-00004-of-00004.safetensors",
984
+ "single_transformer_blocks.23.attn.to_q.bias": "model-00004-of-00004.safetensors",
985
+ "single_transformer_blocks.23.attn.to_k.qweight": "model-00004-of-00004.safetensors",
986
+ "single_transformer_blocks.23.attn.to_k.qzeros": "model-00004-of-00004.safetensors",
987
+ "single_transformer_blocks.23.attn.to_k.scales": "model-00004-of-00004.safetensors",
988
+ "single_transformer_blocks.23.attn.to_k.bias": "model-00004-of-00004.safetensors",
989
+ "single_transformer_blocks.23.attn.to_v.qweight": "model-00004-of-00004.safetensors",
990
+ "single_transformer_blocks.23.attn.to_v.qzeros": "model-00004-of-00004.safetensors",
991
+ "single_transformer_blocks.23.attn.to_v.scales": "model-00004-of-00004.safetensors",
992
+ "single_transformer_blocks.23.attn.to_v.bias": "model-00004-of-00004.safetensors",
993
+ "single_transformer_blocks.24.norm.linear.qweight": "model-00004-of-00004.safetensors",
994
+ "single_transformer_blocks.24.norm.linear.qzeros": "model-00004-of-00004.safetensors",
995
+ "single_transformer_blocks.24.norm.linear.scales": "model-00004-of-00004.safetensors",
996
+ "single_transformer_blocks.24.norm.linear.bias": "model-00004-of-00004.safetensors",
997
+ "single_transformer_blocks.24.proj_mlp.qweight": "model-00004-of-00004.safetensors",
998
+ "single_transformer_blocks.24.proj_mlp.qzeros": "model-00004-of-00004.safetensors",
999
+ "single_transformer_blocks.24.proj_mlp.scales": "model-00004-of-00004.safetensors",
1000
+ "single_transformer_blocks.24.proj_mlp.bias": "model-00004-of-00004.safetensors",
1001
+ "single_transformer_blocks.24.proj_out.qweight": "model-00004-of-00004.safetensors",
1002
+ "single_transformer_blocks.24.proj_out.qzeros": "model-00004-of-00004.safetensors",
1003
+ "single_transformer_blocks.24.proj_out.scales": "model-00004-of-00004.safetensors",
1004
+ "single_transformer_blocks.24.proj_out.bias": "model-00004-of-00004.safetensors",
1005
+ "single_transformer_blocks.24.attn.norm_q.weight": "model-00004-of-00004.safetensors",
1006
+ "single_transformer_blocks.24.attn.norm_k.weight": "model-00004-of-00004.safetensors",
1007
+ "single_transformer_blocks.24.attn.to_q.qweight": "model-00004-of-00004.safetensors",
1008
+ "single_transformer_blocks.24.attn.to_q.qzeros": "model-00004-of-00004.safetensors",
1009
+ "single_transformer_blocks.24.attn.to_q.scales": "model-00004-of-00004.safetensors",
1010
+ "single_transformer_blocks.24.attn.to_q.bias": "model-00004-of-00004.safetensors",
1011
+ "single_transformer_blocks.24.attn.to_k.qweight": "model-00004-of-00004.safetensors",
1012
+ "single_transformer_blocks.24.attn.to_k.qzeros": "model-00004-of-00004.safetensors",
1013
+ "single_transformer_blocks.24.attn.to_k.scales": "model-00004-of-00004.safetensors",
1014
+ "single_transformer_blocks.24.attn.to_k.bias": "model-00004-of-00004.safetensors",
1015
+ "single_transformer_blocks.24.attn.to_v.qweight": "model-00004-of-00004.safetensors",
1016
+ "single_transformer_blocks.24.attn.to_v.qzeros": "model-00004-of-00004.safetensors",
1017
+ "single_transformer_blocks.24.attn.to_v.scales": "model-00004-of-00004.safetensors",
1018
+ "single_transformer_blocks.24.attn.to_v.bias": "model-00004-of-00004.safetensors",
1019
+ "single_transformer_blocks.25.norm.linear.qweight": "model-00004-of-00004.safetensors",
1020
+ "single_transformer_blocks.25.norm.linear.qzeros": "model-00004-of-00004.safetensors",
1021
+ "single_transformer_blocks.25.norm.linear.scales": "model-00004-of-00004.safetensors",
1022
+ "single_transformer_blocks.25.norm.linear.bias": "model-00004-of-00004.safetensors",
1023
+ "single_transformer_blocks.25.proj_mlp.qweight": "model-00004-of-00004.safetensors",
1024
+ "single_transformer_blocks.25.proj_mlp.qzeros": "model-00004-of-00004.safetensors",
1025
+ "single_transformer_blocks.25.proj_mlp.scales": "model-00004-of-00004.safetensors",
1026
+ "single_transformer_blocks.25.proj_mlp.bias": "model-00004-of-00004.safetensors",
1027
+ "single_transformer_blocks.25.proj_out.qweight": "model-00004-of-00004.safetensors",
1028
+ "single_transformer_blocks.25.proj_out.qzeros": "model-00004-of-00004.safetensors",
1029
+ "single_transformer_blocks.25.proj_out.scales": "model-00004-of-00004.safetensors",
1030
+ "single_transformer_blocks.25.proj_out.bias": "model-00004-of-00004.safetensors",
1031
+ "single_transformer_blocks.25.attn.norm_q.weight": "model-00004-of-00004.safetensors",
1032
+ "single_transformer_blocks.25.attn.norm_k.weight": "model-00004-of-00004.safetensors",
1033
+ "single_transformer_blocks.25.attn.to_q.qweight": "model-00004-of-00004.safetensors",
1034
+ "single_transformer_blocks.25.attn.to_q.qzeros": "model-00004-of-00004.safetensors",
1035
+ "single_transformer_blocks.25.attn.to_q.scales": "model-00004-of-00004.safetensors",
1036
+ "single_transformer_blocks.25.attn.to_q.bias": "model-00004-of-00004.safetensors",
1037
+ "single_transformer_blocks.25.attn.to_k.qweight": "model-00004-of-00004.safetensors",
1038
+ "single_transformer_blocks.25.attn.to_k.qzeros": "model-00004-of-00004.safetensors",
1039
+ "single_transformer_blocks.25.attn.to_k.scales": "model-00004-of-00004.safetensors",
1040
+ "single_transformer_blocks.25.attn.to_k.bias": "model-00004-of-00004.safetensors",
1041
+ "single_transformer_blocks.25.attn.to_v.qweight": "model-00004-of-00004.safetensors",
1042
+ "single_transformer_blocks.25.attn.to_v.qzeros": "model-00004-of-00004.safetensors",
1043
+ "single_transformer_blocks.25.attn.to_v.scales": "model-00004-of-00004.safetensors",
1044
+ "single_transformer_blocks.25.attn.to_v.bias": "model-00004-of-00004.safetensors",
1045
+ "single_transformer_blocks.26.norm.linear.qweight": "model-00004-of-00004.safetensors",
1046
+ "single_transformer_blocks.26.norm.linear.qzeros": "model-00004-of-00004.safetensors",
1047
+ "single_transformer_blocks.26.norm.linear.scales": "model-00004-of-00004.safetensors",
1048
+ "single_transformer_blocks.26.norm.linear.bias": "model-00004-of-00004.safetensors",
1049
+ "single_transformer_blocks.26.proj_mlp.qweight": "model-00004-of-00004.safetensors",
1050
+ "single_transformer_blocks.26.proj_mlp.qzeros": "model-00004-of-00004.safetensors",
1051
+ "single_transformer_blocks.26.proj_mlp.scales": "model-00004-of-00004.safetensors",
1052
+ "single_transformer_blocks.26.proj_mlp.bias": "model-00004-of-00004.safetensors",
1053
+ "single_transformer_blocks.26.proj_out.qweight": "model-00004-of-00004.safetensors",
1054
+ "single_transformer_blocks.26.proj_out.qzeros": "model-00004-of-00004.safetensors",
1055
+ "single_transformer_blocks.26.proj_out.scales": "model-00004-of-00004.safetensors",
1056
+ "single_transformer_blocks.26.proj_out.bias": "model-00004-of-00004.safetensors",
1057
+ "single_transformer_blocks.26.attn.norm_q.weight": "model-00004-of-00004.safetensors",
1058
+ "single_transformer_blocks.26.attn.norm_k.weight": "model-00004-of-00004.safetensors",
1059
+ "single_transformer_blocks.26.attn.to_q.qweight": "model-00004-of-00004.safetensors",
1060
+ "single_transformer_blocks.26.attn.to_q.qzeros": "model-00004-of-00004.safetensors",
1061
+ "single_transformer_blocks.26.attn.to_q.scales": "model-00004-of-00004.safetensors",
1062
+ "single_transformer_blocks.26.attn.to_q.bias": "model-00004-of-00004.safetensors",
1063
+ "single_transformer_blocks.26.attn.to_k.qweight": "model-00004-of-00004.safetensors",
1064
+ "single_transformer_blocks.26.attn.to_k.qzeros": "model-00004-of-00004.safetensors",
1065
+ "single_transformer_blocks.26.attn.to_k.scales": "model-00004-of-00004.safetensors",
1066
+ "single_transformer_blocks.26.attn.to_k.bias": "model-00004-of-00004.safetensors",
1067
+ "single_transformer_blocks.26.attn.to_v.qweight": "model-00004-of-00004.safetensors",
1068
+ "single_transformer_blocks.26.attn.to_v.qzeros": "model-00004-of-00004.safetensors",
1069
+ "single_transformer_blocks.26.attn.to_v.scales": "model-00004-of-00004.safetensors",
1070
+ "single_transformer_blocks.26.attn.to_v.bias": "model-00004-of-00004.safetensors",
1071
+ "timestep_embedder.linear_1.weight": "model-00004-of-00004.safetensors",
1072
+ "timestep_embedder.linear_1.bias": "model-00004-of-00004.safetensors",
1073
+ "timestep_embedder.linear_2.weight": "model-00004-of-00004.safetensors",
1074
+ "timestep_embedder.linear_2.bias": "model-00004-of-00004.safetensors",
1075
+ "context_embedder_norm.weight": "model-00004-of-00004.safetensors",
1076
+ "context_embedder.weight": "model-00004-of-00004.safetensors",
1077
+ "context_embedder.bias": "model-00004-of-00004.safetensors",
1078
+ "x_embedder.weight": "model-00004-of-00004.safetensors",
1079
+ "x_embedder.bias": "model-00004-of-00004.safetensors",
1080
+ "norm_out.linear.weight": "model-00004-of-00004.safetensors",
1081
+ "norm_out.linear.bias": "model-00004-of-00004.safetensors",
1082
+ "proj_out.weight": "model-00004-of-00004.safetensors",
1083
+ "proj_out.bias": "model-00004-of-00004.safetensors"
1084
+ }
1085
+ }
transformer/quantization_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "data_type": "int",
4
+ "group_size": 128,
5
+ "sym": true,
6
+ "batch_size": 1,
7
+ "nsamples": 64,
8
+ "autoround_version": "0.13.0",
9
+ "block_name_to_quantize": "transformer_blocks,single_transformer_blocks",
10
+ "quant_method": "auto-round",
11
+ "packing_format": "auto_round:auto_gptq"
12
+ }
vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "/mnt/disk4/lvl/Ovis-Image-7B/vae",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 16,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "mid_block_add_attention": true,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 3,
27
+ "sample_size": 1024,
28
+ "scaling_factor": 0.3611,
29
+ "shift_factor": 0.1159,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": false,
37
+ "use_quant_conv": false
38
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3
3
+ size 167666902