{
  "model_type": "manthan_m1",
  "architectures": [
    "ManthanM1"
  ],
  "vlm_config": {
    "vision_config": {
      "return_dict": true,
      "output_hidden_states": false,
      "dtype": null,
      "chunk_size_feed_forward": 0,
      "is_encoder_decoder": false,
      "architectures": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "problem_type": null,
      "_name_or_path": "",
      "model_type": "qwen3_vl",
      "depth": 24,
      "hidden_size": 1024,
      "hidden_act": "gelu_pytorch_tanh",
      "intermediate_size": 4096,
      "num_heads": 16,
      "in_channels": 3,
      "patch_size": 16,
      "spatial_merge_size": 2,
      "temporal_patch_size": 2,
      "out_hidden_size": 2560,
      "num_position_embeddings": 2304,
      "initializer_range": 0.02,
      "deepstack_visual_indexes": [
        5,
        11,
        17
      ],
      "output_attentions": false
    },
    "text_config": {
      "vocab_size": 151936,
      "max_position_embeddings": 262144,
      "hidden_size": 2560,
      "intermediate_size": 9728,
      "num_hidden_layers": 36,
      "num_attention_heads": 32,
      "num_key_value_heads": 8,
      "head_dim": 128,
      "hidden_act": "silu",
      "initializer_range": 0.02,
      "rms_norm_eps": 1e-06,
      "use_cache": true,
      "attention_bias": false,
      "attention_dropout": 0.0,
      "rope_parameters": {
        "mrope_interleaved": true,
        "mrope_section": [
          24,
          20,
          20
        ],
        "rope_type": "default",
        "rope_theta": 5000000
      },
      "pad_token_id": null,
      "return_dict": true,
      "output_hidden_states": false,
      "dtype": "bfloat16",
      "chunk_size_feed_forward": 0,
      "is_encoder_decoder": false,
      "architectures": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "problem_type": null,
      "_name_or_path": "",
      "bos_token_id": 151643,
      "eos_token_id": 151645,
      "model_type": "qwen3_vl_text",
      "tie_word_embeddings": true,
      "output_attentions": false
    },
    "image_token_id": 151655,
    "video_token_id": 151656,
    "vision_start_token_id": 151652,
    "vision_end_token_id": 151653,
    "tie_word_embeddings": true,
    "return_dict": true,
    "output_hidden_states": false,
    "dtype": null,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "architectures": [
      "Qwen3VLForConditionalGeneration"
    ],
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "problem_type": null,
    "_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
    "transformers_version": "5.2.0",
    "model_type": "qwen3_vl",
    "output_attentions": false
  },
  "llm_config": {
    "vocab_size": 201088,
    "hidden_size": 2880,
    "intermediate_size": 2880,
    "num_hidden_layers": 24,
    "num_attention_heads": 64,
    "num_local_experts": 32,
    "sliding_window": 128,
    "num_experts_per_tok": 4,
    "num_key_value_heads": 8,
    "hidden_act": "silu",
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-05,
    "attention_dropout": 0.0,
    "head_dim": 64,
    "layer_types": [
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "full_attention"
    ],
    "attention_bias": true,
    "max_position_embeddings": 131072,
    "router_aux_loss_coef": 0.9,
    "output_router_logits": false,
    "use_cache": true,
    "rope_parameters": {
      "beta_fast": 32.0,
      "beta_slow": 1.0,
      "factor": 32.0,
      "original_max_position_embeddings": 4096,
      "rope_type": "yarn",
      "truncate": false,
      "rope_theta": 150000
    },
    "tie_word_embeddings": false,
    "pad_token_id": 199999,
    "bos_token_id": null,
    "eos_token_id": 200002,
    "return_dict": true,
    "output_hidden_states": false,
    "dtype": null,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "architectures": [
      "GptOssForCausalLM"
    ],
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "problem_type": null,
    "_name_or_path": "openai/gpt-oss-20b",
    "transformers_version": "5.2.0",
    "experts_per_token": 4,
    "initial_context_length": 4096,
    "model_type": "gpt_oss",
    "quantization_config": {
      "modules_to_not_convert": [
        "model.layers.*.self_attn",
        "model.layers.*.mlp.router",
        "model.embed_tokens",
        "lm_head"
      ],
      "quant_method": "mxfp4"
    },
    "swiglu_limit": 7.0,
    "output_attentions": false
  },
  "vlm_system_prompt": "Analyze this image comprehensively. Describe the main subjects, background, text (OCR), spatial relationships, colors, and any notable details. Output in a structured format."
}