| { | |
| "_name_or_path": "apple/DCLM-Baseline-7B", | |
| "apply_qk_norm": true, | |
| "architectures": [ | |
| "OpenLMForCausalLM" | |
| ], | |
| "attn_activation": null, | |
| "attn_name": "torch_attn", | |
| "attn_seq_scalar": null, | |
| "attn_seq_scalar_alpha": null, | |
| "dim": 4096, | |
| "ffn_type": "swiglu_torch", | |
| "model": "open_lm_7b", | |
| "model_type": "openlm", | |
| "moe_capacity_factor": 1.25, | |
| "moe_expert_model_parallelism": false, | |
| "moe_freq": 0, | |
| "moe_loss_weight": 0.1, | |
| "moe_num_experts": null, | |
| "moe_top_k": 2, | |
| "moe_weight_parallelism": false, | |
| "n_heads": 32, | |
| "n_layers": 32, | |
| "norm_eps": 1e-05, | |
| "norm_type": "gain_only_lp_layer_norm", | |
| "params": null, | |
| "positional_embedding_type": "rotary", | |
| "post_embed_norm": false, | |
| "qk_norm": true, | |
| "seq_len": 2048, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.4", | |
| "vocab_size": 50432, | |
| "weight_tying": false | |
| } | |