Qwen/CodeQwen1.5-7B
1051.8k
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 2,7 "eos_token_id": 2,8 "hidden_act": "silu",9 "hidden_size": 4096,10 "initializer_range": 0.02,11 "intermediate_size": 13440,12 "max_position_embeddings": 65536,13 "max_window_layers": 28,14 "model_type": "qwen2",15 "num_attention_heads": 32,16 "num_hidden_layers": 32,17 "num_key_value_heads": 4,18 "rms_norm_eps": 1e-05,19 "rope_theta": 1000000,20 "rotary_emb_base": 1000000,21 "seq_length": 65536,22 "sliding_window": 65536,23 "tie_word_embeddings": false,24 "torch_dtype": "bfloat16",25 "transformers_version": "4.39.3",26 "use_cache": true,27 "use_sliding_window": false,28 "vocab_size": 9241629}30 