model_config.json

{
    "type": "onnxmodel",
    "config": {
        "model_path": "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml",
        "onnx_file_name": "model.onnx",
        "inference_settings": null,
        "use_ort_extensions": false,
        "external_initializers_file_name": null,
        "constant_inputs_file_name": null,
        "model_attributes": {
            "vocab_size": 151936,
            "max_position_embeddings": 40960,
            "hidden_size": 5120,
            "intermediate_size": 17408,
            "num_hidden_layers": 40,
            "num_attention_heads": 40,
            "use_sliding_window": false,
            "sliding_window": null,
            "max_window_layers": 40,
            "num_key_value_heads": 8,
            "head_dim": 128,
            "hidden_act": "silu",
            "initializer_range": 0.02,
            "rms_norm_eps": 1e-06,
            "use_cache": true,
            "rope_theta": 1000000,
            "rope_scaling": null,
            "attention_bias": false,
            "attention_dropout": 0.0,
            "layer_types": [
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention"
            ],
            "return_dict": true,
            "output_hidden_states": false,
            "torchscript": false,
            "dtype": "bfloat16",
            "pruned_heads": {},
            "tie_word_embeddings": false,
            "chunk_size_feed_forward": 0,
            "is_encoder_decoder": false,
            "is_decoder": false,
            "cross_attention_hidden_size": null,
            "add_cross_attention": false,
            "tie_encoder_decoder": false,
            "architectures": [
                "Qwen3ForCausalLM"
            ],
            "finetuning_task": null,
            "id2label": {
                "0": "LABEL_0",
                "1": "LABEL_1"
            },
            "label2id": {
                "LABEL_0": 0,
                "LABEL_1": 1
            },
            "task_specific_params": null,
            "problem_type": null,
            "tokenizer_class": null,
            "prefix": null,
            "bos_token_id": 151643,
            "pad_token_id": null,
            "eos_token_id": 151645,
            "sep_token_id": null,
            "decoder_start_token_id": null,
            "max_length": 20,
            "min_length": 0,
            "do_sample": false,
            "early_stopping": false,
            "num_beams": 1,
            "temperature": 1.0,
            "top_k": 50,
            "top_p": 1.0,
            "typical_p": 1.0,
            "repetition_penalty": 1.0,
            "length_penalty": 1.0,
            "no_repeat_ngram_size": 0,
            "encoder_no_repeat_ngram_size": 0,
            "bad_words_ids": null,
            "num_return_sequences": 1,
            "output_scores": false,
            "return_dict_in_generate": false,
            "forced_bos_token_id": null,
            "forced_eos_token_id": null,
            "remove_invalid_values": false,
            "exponential_decay_length_penalty": null,
            "suppress_tokens": null,
            "begin_suppress_tokens": null,
            "num_beam_groups": 1,
            "diversity_penalty": 0.0,
            "_name_or_path": "OpenPipe/Qwen3-14B-Instruct",
            "transformers_version": "4.57.6",
            "model_type": "qwen3",
            "tf_legacy_loss": false,
            "use_bfloat16": false,
            "output_attentions": false,
            "additional_files": [
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\added_tokens.json",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\chat_template.jinja",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\config.json",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\genai_config.json",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\generation_config.json",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\merges.txt",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\special_tokens_map.json",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\tokenizer.json",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\tokenizer_config.json",
                "D:\\Documents\\Qwen3-14B-Instruct\\out_qwen3_14b_int4_dml\\vocab.json"
            ]
        }
    }
}