| { | |
| "architectures": [ | |
| "DeciLlamaForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_decicoder.DeciCoderConfig", | |
| "AutoModelForCausalLM": "modeling_decicoder.DeciCoderForCausalLM" | |
| }, | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5888, | |
| "max_position_embeddings": 2048, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 20, | |
| "num_key_value_heads": 4, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "use_bfloat16": true, | |
| "transformers_version": "4.31.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| } |