| { | |
| "_name_or_path": "wtang06/mpt-125m-c4", | |
| "architectures": [ | |
| "MPTForCausalLM" | |
| ], | |
| "attn_config": { | |
| "alibi": false, | |
| "model_type": "" | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "wtang06/mpt-125m-c4--configuration_mpt.MPTConfig", | |
| "AutoModelForCausalLM": "wtang06/mpt-125m-c4--modeling_mpt.MPTForCausalLM" | |
| }, | |
| "d_model": 768, | |
| "emb_pdrop": 0.0, | |
| "embedding_fraction": 1.0, | |
| "expansion_ratio": 4, | |
| "fc_type": "torch", | |
| "ffn_config": { | |
| "fc_type": "torch", | |
| "ffn_type": "mptmlp" | |
| }, | |
| "init_config": { | |
| "emb_init_std": null, | |
| "emb_init_uniform_lim": null, | |
| "fan_mode": "fan_in", | |
| "init_div_is_residual": true, | |
| "init_gain": 0.0, | |
| "init_nonlinearity": "relu", | |
| "init_std": null, | |
| "name": "kaiming_normal_" | |
| }, | |
| "init_device": "cpu", | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "learned_pos_emb": true, | |
| "logit_scale": null, | |
| "max_seq_len": 2048, | |
| "model_type": "mpt", | |
| "n_heads": 8, | |
| "n_layers": 12, | |
| "no_bias": false, | |
| "norm_type": "low_precision_layernorm", | |
| "resid_pdrop": 0.0, | |
| "transformers_version": "4.35.2", | |
| "use_cache": false, | |
| "verbose": 0, | |
| "vocab_size": 50368 | |
| } | |