transformer/config.json

{
  "_class_name": "CogVideoXTransformer3DModel",
  "_diffusers_version": "0.31.0.dev0",
  "_name_or_path": "/raid/aryan/CogVideoX-5b-trial",
  "activation_fn": "gelu-approximate",
  "attention_bias": true,
  "attention_head_dim": 64,
  "dropout": 0.0,
  "flip_sin_to_cos": true,
  "freq_shift": 0,
  "in_channels": 16,
  "max_text_seq_length": 226,
  "norm_elementwise_affine": true,
  "norm_eps": 1e-05,
  "num_attention_heads": 48,
  "num_layers": 42,
  "out_channels": 16,
  "patch_size": 2,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "sample_frames": 49,
  "sample_height": 60,
  "sample_width": 90,
  "spatial_interpolation_scale": 1.875,
  "temporal_compression_ratio": 4,
  "temporal_interpolation_scale": 1.0,
  "text_embed_dim": 4096,
  "time_embed_dim": 512,
  "timestep_activation_fn": "silu",
  "use_rotary_positional_embeddings": true
}