| { | |
| "architectures": [ | |
| "HanForgeForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1408, | |
| "max_position_embeddings": 4096, | |
| "model_type": "hanforge", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 50000.0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.5.1", | |
| "unk_token_id": 3, | |
| "use_cache": false, | |
| "vocab_size": 24000, | |
| "auto_map": { | |
| "AutoConfig": "configuration_hanforge.HanForgeConfig", | |
| "AutoModelForCausalLM": "modeling_hanforge.HanForgeForCausalLM" | |
| }, | |
| "torch_dtype": "float32" | |
| } |