cnfusion/MusaCoder-27B-mlx-3Bit
07
1{2 "architectures": [3 "Qwen3_5ForConditionalGeneration"4 ],5 "bos_token_id": null,6 "dtype": "bfloat16",7 "eos_token_id": [8 248046,9 24804410 ],11 "hidden_size": 5120,12 "image_token_id": 248056,13 "language_model_only": false,14 "model_type": "qwen3_5",15 "pad_token_id": 248044,16 "quantization": {17 "group_size": 64,18 "bits": 3,19 "mode": "affine"20 },21 "quantization_config": {22 "group_size": 64,23 "bits": 3,24 "mode": "affine"25 },26 "text_config": {27 "attention_bias": false,28 "attention_dropout": 0.0,29 "attn_output_gate": true,30 "bos_token_id": 248044,31 "dtype": "bfloat16",32 "eos_token_id": 248044,33 "full_attention_interval": 4,34 "head_dim": 256,35 "hidden_act": "silu",36 "hidden_size": 5120,37 "initializer_range": 0.02,38 "intermediate_size": 17408,39 "layer_types": [40 "linear_attention",41 "linear_attention",42 "linear_attention",43 "full_attention",44 "linear_attention",45 "linear_attention",46 "linear_attention",47 "full_attention",48 "linear_attention",49 "linear_attention",50 "linear_attention",51 "full_attention",52 "linear_attention",53 "linear_attention",54 "linear_attention",55 "full_attention",56 "linear_attention",57 "linear_attention",58 "linear_attention",59 "full_attention",60 "linear_attention",61 "linear_attention",62 "linear_attention",63 "full_attention",64 "linear_attention",65 "linear_attention",66 "linear_attention",67 "full_attention",68 "linear_attention",69 "linear_attention",70 "linear_attention",71 "full_attention",72 "linear_attention",73 "linear_attention",74 "linear_attention",75 "full_attention",76 "linear_attention",77 "linear_attention",78 "linear_attention",79 "full_attention",80 "linear_attention",81 "linear_attention",82 "linear_attention",83 "full_attention",84 "linear_attention",85 "linear_attention",86 "linear_attention",87 "full_attention",88 "linear_attention",89 "linear_attention",90 "linear_attention",91 "full_attention",92 "linear_attention",93 "linear_attention",94 "linear_attention",95 "full_attention",96 "linear_attention",97 "linear_attention",98 "linear_attention",99 "full_attention",100 "linear_attention",101 "linear_attention",102 "linear_attention",103 "full_attention"104 ],105 "linear_conv_kernel_dim": 4,106 "linear_key_head_dim": 128,107 "linear_num_key_heads": 16,108 "linear_num_value_heads": 48,109 "linear_value_head_dim": 128,110 "mamba_ssm_dtype": "float32",111 "max_position_embeddings": 262144,112 "model_type": "qwen3_5_text",113 "mtp_num_hidden_layers": 1,114 "mtp_use_dedicated_embeddings": false,115 "num_attention_heads": 24,116 "num_hidden_layers": 64,117 "num_key_value_heads": 4,118 "output_gate_type": "swish",119 "pad_token_id": 248044,120 "partial_rotary_factor": 0.25,121 "rms_norm_eps": 1e-06,122 "rope_parameters": {123 "mrope_interleaved": true,124 "mrope_section": [125 11,126 11,127 10128 ],129 "partial_rotary_factor": 0.25,130 "rope_theta": 10000000,131 "type": "default"132 },133 "tie_word_embeddings": false,134 "use_cache": false,135 "vocab_size": 248320136 },137 "tie_word_embeddings": false,138 "transformers_version": "5.2.0",139 "use_cache": false,140 "video_token_id": 248057,141 "vision_end_token_id": 248054,142 "vision_start_token_id": 248053143}