openpangu/openPangu-R-7B-Diffusion
036
1{2 "architectures": [3 "PanguEmbeddedForCausalLM"4 ],5 "auto_map": {6 "AutoConfig": "configuration_openpangu_dense.PanguEmbeddedConfig",7 "AutoModel": "modeling_openpangu_dense.PanguEmbeddedModel",8 "AutoModelForCausalLM": "modeling_openpangu_dense.PanguEmbeddedForCausalLM"9 },10 "bias": true,11 "attention_dropout": 0.0,12 "bos_token_id": 1,13 "pad_token_id": 0,14 "eos_token_id": 45892,15 "hidden_act": "silu",16 "hidden_size": 4096,17 "initializer_range": 0.02,18 "intermediate_size": 12800,19 "max_position_embeddings": 32768,20 "model_type": "PanguEmbedded",21 "num_attention_heads": 32,22 "num_hidden_layers": 34,23 "num_key_value_heads": 8,24 "rms_norm_eps": 1e-06,25 "rope_theta": 16000000.0,26 "tie_word_embeddings": false,27 "torch_dtype": "bfloat16",28 "transformers_version": "4.53.2",29 "use_cache": true,30 "vocab_size": 15337631}32 