| { | |
| "_name_or_path": "mpt-340m-pruned", | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "MptForCausalLM" | |
| ], | |
| "attention_matrix_factorization_rank": 128, | |
| "attn_config": { | |
| "alibi_bias_max": 16, | |
| "clip_qkv": 6, | |
| "model_type": "" | |
| }, | |
| "attn_pdrop": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "mosaicml/mpt-7b-storywriter--configuration_mpt.MPTConfig", | |
| "AutoModelForCausalLM": "mosaicml/mpt-7b-storywriter--modeling_mpt.MPTForCausalLM" | |
| }, | |
| "d_model": 1280, | |
| "emb_pdrop": 0, | |
| "embedding_fraction": 1.0, | |
| "expansion_ratio": 4, | |
| "feedforward_matrix_factorization_rank": 128, | |
| "init_config": { | |
| "emb_init_std": null, | |
| "emb_init_uniform_lim": null, | |
| "fan_mode": "fan_in", | |
| "init_div_is_residual": true, | |
| "init_gain": 0, | |
| "init_nonlinearity": "relu", | |
| "init_std": 0.02, | |
| "name": "kaiming_normal_", | |
| "verbose": 0 | |
| }, | |
| "init_device": "cpu", | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "learned_pos_emb": true, | |
| "logit_scale": null, | |
| "max_seq_len": 65536, | |
| "model_type": "mpt", | |
| "n_heads": 20, | |
| "n_layers": 14, | |
| "no_bias": true, | |
| "norm_type": "low_precision_layernorm", | |
| "quantization_aware_training": true, | |
| "resid_pdrop": 0.0, | |
| "tokenizer_name": "EleutherAI/gpt-neox-20b", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.44.2", | |
| "use_cache": true, | |
| "use_early_exiting": true, | |
| "use_reversible_layers": true, | |
| "verbose": 0, | |
| "vocab_size": 50432 | |
| } | |