{ "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoTokenizer": [ "tokenization_pinyin_code.EncodedMandarinTokenizer", "tokenization_pinyin_code.EncodedMandarinTokenizerFast" ] }, "bos_token_id": 2, "eos_token_id": 3, "evaluation_backend": "causal", "hidden_act": "silu", "hidden_size": 512, "initializer_range": 0.02, "intermediate_size": 1376, "max_position_embeddings": 512, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 8, "num_hidden_layers": 8, "num_key_value_heads": 4, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": true, "torch_dtype": "float32", "transformers_version": "4.41.2", "unk_token_id": 1, "use_cache": true, "use_sliding_window": false, "vocab_size": 16000 }