| { | |
| "architectures": [ | |
| "MptForCausalLM" | |
| ], | |
| "attn_config": { | |
| "model_type": "" | |
| }, | |
| "d_model": 256, | |
| "emb_pdrop": 0.0, | |
| "embedding_fraction": 1.0, | |
| "expansion_ratio": 4, | |
| "hidden_act": "gelu", | |
| "init_device": "cpu", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "layer_norm_epsilon": 1e-05, | |
| "learned_pos_emb": true, | |
| "logit_scale": null, | |
| "max_seq_len": 2048, | |
| "model_type": "mpt", | |
| "n_heads": 8, | |
| "n_layers": 2, | |
| "no_bias": true, | |
| "norm_type": "low_precision_layernorm", | |
| "num_key_value_heads": 8, | |
| "resid_pdrop": 0.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.4", | |
| "use_cache": false, | |
| "verbose": 0, | |
| "vocab_size": 2000 | |
| } | |