Hugging Face's logo

Floki00
/
cirdit_multimodal_compile_3to5qubit

Other
Safetensors
genQC
physics
diffusion-model
quantum-information
quantum-circuits
Model card Files
xet
 Community
1
cirdit_multimodal_compile_3to5qubit
File size: 2,763 Bytes
fc1456f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
target: genQC.pipeline.multimodal_diffusion_pipeline.MultimodalDiffusionPipeline_ParametrizedCompilation
params:
  scheduler:
    target: genQC.scheduler.scheduler_ddim.DDIMScheduler
    params:
      device: cpu
      num_train_timesteps: 1000
      beta_start: 0.001
      beta_end: 0.012
      beta_schedule: "path:beta_schedule_learned_linear.safetensors"
      input_perturbation: 0.0
      prediction_type: v-type
  scheduler_w:
    target: genQC.scheduler.scheduler_ddim.DDIMScheduler
    params:
      device: cpu
      num_train_timesteps: 1000
      beta_start: 0.0002
      beta_end: 0.024
      beta_schedule: cos_alpha4
      input_perturbation: 0.0
      prediction_type: v-type
  model:
    target: genQC.models.transformers.cirdit_multimodal.UnitaryCLIPPartialNoiseCompilationCirDiT
    save_type: safetensors
    params:
      clr_dim: 16
      ch_packing: 384
      ch_core: 1024
      c_emb_size: 640
      t_emb_size: 512
      depth_packing: 6
      depth_core: 12
      num_heads_packing: 12
      num_heads_core: 16
      dropout: 0.0
      p_rope: 0.9
      base_rope: 1000.0
      unitary_encoder_config:
        target: genQC.models.clip.unitary_clip.UnitaryTextEncoder
        params:
          text_embed_ch: 512
          text_encoding_ch: 128
          text_attn_num_heads: 8
          text_attn_depth: 1
          unitary_encoding_ch: 40
          unitary_downscale_factor: 4
          main_num_heads: 16
          main_depth: 8
          use_rope: false
          p_rope: 0.9
          base_rope: 1000.0
          dropout: 0.1
  text_encoder:
    target: genQC.models.clip.frozen_open_clip.CachedFrozenOpenCLIPEmbedder
    params:
      arch: ViT-B-32
      version: datacomp_xl_s13b_b90k
      #device: cpu
      max_length: 37
      freeze: true
      layer: penultimate
      enable_cache_token_limit: true
  embedder:
    target: genQC.models.embedding.rotational_preset_embedder.RotationalMultimodialPresetEmbedderTiny
    save_type: safetensors
    params:
      clr_dim: 13
      num_clrs: 12
      params_dim: 3
      num_params_per_clr: 1
      zero_sum_space: true
      explicit_node_type_embeddings: false
      channel_last: true
      parametrized_tokens:
      - 5
      - 6
      - 7
      - 8
      unique_class_values:
      - -3
      - -2
      - 0
      - 1
      - 2
      - 3
      - 4
      - 5
      - 6
      - 7
      - 8
      - 9
  device: cpu
  enable_guidance_train: true
  guidance_train_p: 0.1
  cached_text_enc: true
  add_config:
    dataset:
      params:
        pad_constant: 9
        num_of_qubits: 5
        min_gates: 4
        max_gates: 32
        max_params: 1
        gate_pool:
        - h
        - cx
        - ccx
        - swap
        - rx
        - ry
        - rz
        - cp