text_encoder/config.json

{
  "architectures": [
    "Qwen3VLForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "image_token_id": 151655,
  "model_type": "qwen3_vl",
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "lm_head",
      "visual"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 12288,
    "max_position_embeddings": 262144,
    "model_type": "qwen3_vl_text",
    "num_attention_heads": 32,
    "num_hidden_layers": 36,
    "num_key_value_heads": 8,
    "pad_token_id": null,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "mrope_interleaved": true,
      "mrope_section": [
        24,
        20,
        20
      ],
      "rope_theta": 5000000,
      "rope_type": "default"
    },
    "use_cache": true,
    "vocab_size": 151936
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.17.0",
  "video_token_id": 151656,
  "vision_config": {
    "deepstack_visual_indexes": [
      8,
      16,
      24
    ],
    "depth": 27,
    "dtype": "bfloat16",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 4304,
    "model_type": "qwen3_vl_vision",
    "num_heads": 16,
    "num_position_embeddings": 2304,
    "out_hidden_size": 4096,
    "patch_size": 16,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "axial"
    },
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "_modification_notice": "Modified by ixim / iximbox: eligible linear weights converted from Qwen-Image-2.1 to bitsandbytes LLM.int8 INT8. Built with Qwen. Non-commercial research/evaluation under the accompanying Qwen Research License."
}