| { | |
| "architectures": [ | |
| "MyGrokForCausalLM" | |
| ], | |
| "model_type": "my_grok", | |
| "vocab_size": 13816, | |
| "hidden_size": 512, | |
| "intermediate_size": 1376, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 8, | |
| "num_key_value_heads": 2, | |
| "max_position_embeddings": 2048, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "pad_token_id": 0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.36.0", | |
| "auto_map": { | |
| "AutoConfig": "modeling_my_grok.MyGrokConfig", | |
| "AutoModelForCausalLM": "modeling_my_grok.MyGrokForCausalLM" | |
| } | |
| } |