config.json

{
  "action_dim": 32,
  "action_head_cfg": {
    "action_dim": 32,
    "action_horizon": 16,
    "add_pos_embed": true,
    "backbone_embedding_dim": 2048,
    "diffusion_model_cfg": {
      "attention_head_dim": 48,
      "cross_attention_dim": 2048,
      "dropout": 0.2,
      "final_dropout": true,
      "interleave_self_attention": true,
      "norm_type": "ada_norm",
      "num_attention_heads": 32,
      "num_layers": 16,
      "output_dim": 1024,
      "positional_embeddings": null
    },
    "hidden_size": 1024,
    "input_embedding_dim": 1536,
    "max_action_dim": 32,
    "max_state_dim": 64,
    "model_dtype": "float32",
    "noise_beta_alpha": 1.5,
    "noise_beta_beta": 1.0,
    "noise_s": 0.999,
    "num_inference_timesteps": 4,
    "num_target_vision_tokens": 32,
    "num_timestep_buckets": 1000,
    "tune_diffusion_model": true,
    "tune_projector": true,
    "use_vlln": true,
    "vl_self_attention_cfg": {
      "attention_head_dim": 64,
      "dropout": 0.2,
      "final_dropout": true,
      "num_attention_heads": 32,
      "num_layers": 4,
      "positional_embeddings": null
    }
  },
  "action_horizon": 16,
  "architectures": [
    "Starforce_S1"
  ],
  "attn_implementation": null,
  "backbone_cfg": {
    "project_to_dim": 2048,
    "select_layer": 12,
    "tune_llm": false,
    "vllm_base_model_path": "checkpoints/Qwen2.5-VL-3B-Instruct"
  },
  "compute_dtype": "bfloat16",
  "model_type": "starforce_s1",
  "torch_dtype": "float32",
  "transformers_version": "4.51.3"
}