Team Ai
Modelpublic

mlboydaisuke/OpenThai-SystemOne-CoreAI

sourceHugging Faceapache-2.0updated 16d agoView on Hugging Face
0likes41downloads
config.json107 linesDownload Raw Back to root
1{2  "abstain_slot": 255,3  "answer_token_id": 248082,4  "architectures": [5    "OpenThaiSystemOneForDecision"6  ],7  "dtype": "bfloat16",8  "head_bias": true,9  "model_type": "openthai_systemone",10  "n_slots": 256,11  "n_temperatures": 3,12  "pad_token_id": 248044,13  "text_config": {14    "_name_or_path": "runs/cpt/latest",15    "architectures": [16      "Qwen3_5ForCausalLM"17    ],18    "attention_bias": false,19    "attention_dropout": 0.0,20    "attn_output_gate": true,21    "bos_token_id": null,22    "chunk_size_feed_forward": 0,23    "dtype": "bfloat16",24    "eos_token_id": 248044,25    "full_attention_interval": 4,26    "head_dim": 256,27    "hidden_act": "silu",28    "hidden_size": 1024,29    "id2label": {30      "0": "LABEL_0",31      "1": "LABEL_1"32    },33    "initializer_range": 0.02,34    "intermediate_size": 3584,35    "is_encoder_decoder": false,36    "label2id": {37      "LABEL_0": 0,38      "LABEL_1": 139    },40    "layer_types": [41      "linear_attention",42      "linear_attention",43      "linear_attention",44      "full_attention",45      "linear_attention",46      "linear_attention",47      "linear_attention",48      "full_attention",49      "linear_attention",50      "linear_attention",51      "linear_attention",52      "full_attention",53      "linear_attention",54      "linear_attention",55      "linear_attention",56      "full_attention",57      "linear_attention",58      "linear_attention",59      "linear_attention",60      "full_attention",61      "linear_attention",62      "linear_attention",63      "linear_attention",64      "full_attention"65    ],66    "linear_conv_kernel_dim": 4,67    "linear_key_head_dim": 128,68    "linear_num_key_heads": 16,69    "linear_num_value_heads": 16,70    "linear_value_head_dim": 128,71    "mamba_ssm_dtype": "float32",72    "max_position_embeddings": 262144,73    "mlp_only_layers": [],74    "model_type": "qwen3_5_text",75    "mtp_num_hidden_layers": 1,76    "mtp_use_dedicated_embeddings": false,77    "num_attention_heads": 8,78    "num_hidden_layers": 24,79    "num_key_value_heads": 2,80    "output_attentions": false,81    "output_hidden_states": false,82    "pad_token_id": null,83    "partial_rotary_factor": 0.25,84    "problem_type": null,85    "return_dict": true,86    "rms_norm_eps": 1e-06,87    "rope_parameters": {88      "mrope_interleaved": true,89      "mrope_section": [90        11,91        11,92        1093      ],94      "partial_rotary_factor": 0.25,95      "rope_theta": 10000000,96      "rope_type": "default"97    },98    "tie_word_embeddings": false,99    "use_cache": true,100    "vocab_size": 248339101  },102  "transformers_version": "5.17.0",103  "auto_map": {104    "AutoConfig": "configuration.OpenThaiSystemOneConfig",105    "AutoModel": "modeling.OpenThaiSystemOneForDecision"106  }107}