| { | |
| "architectures": [ | |
| "TensorMindForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_tensormind.TensorMindConfig", | |
| "AutoModel": "modeling_tensormind.TensorMindModel", | |
| "AutoModelForCausalLM": "modeling_tensormind.TensorMindForCausalLM" | |
| }, | |
| "bos_token_id": null, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 32768, | |
| "model_type": "tensormind", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.1.0", | |
| "use_cache": true, | |
| "vocab_size": 32768 | |
| } | |