| { | |
| "_name_or_path": "/nfs/scistore14/alistgrp/ekurtic/mpt_7b_gsm8k_final/TeacherFixed_frozenEmbedsNO_loss1.0CE_1.0KDlayerwise_oneshot_sparsegpt_sp48_64_4ep_lr1e-4_bs32_noGradClip_warmup20ba/training", | |
| "architectures": [ | |
| "MPTForCausalLM" | |
| ], | |
| "attn_config": { | |
| "alibi": true, | |
| "alibi_bias_max": 8, | |
| "attn_impl": "torch", | |
| "attn_pdrop": 0, | |
| "attn_type": "multihead_attention", | |
| "attn_uses_sequence_id": false, | |
| "clip_qkv": null, | |
| "prefix_lm": false, | |
| "qk_ln": false, | |
| "softmax_scale": null | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "configuration_mpt.MPTConfig", | |
| "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM" | |
| }, | |
| "d_model": 4096, | |
| "emb_pdrop": 0, | |
| "embedding_fraction": 1.0, | |
| "expansion_ratio": 4, | |
| "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", | |
| "learned_pos_emb": true, | |
| "logit_scale": null, | |
| "max_seq_len": 2048, | |
| "model_type": "mpt", | |
| "n_heads": 32, | |
| "n_layers": 32, | |
| "no_bias": true, | |
| "norm_type": "low_precision_layernorm", | |
| "resid_pdrop": 0, | |
| "tokenizer_name": "EleutherAI/gpt-neox-20b", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.32.0.dev0", | |
| "use_cache": false, | |
| "verbose": 0, | |
| "vocab_size": 50432 | |
| } | |