| { | |
| "activation_type": "swiglu", | |
| "alibi": false, | |
| "alibi_bias_max": 8.0, | |
| "architectures": [ | |
| "OLMoForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attention_layer_norm": false, | |
| "attention_layer_norm_with_affine": false, | |
| "bias_for_layer_norm": false, | |
| "block_group_size": 1, | |
| "block_type": "sequential", | |
| "clip_qkv": null, | |
| "d_model": 528, | |
| "emb_init_std": null, | |
| "embedding_dropout": 0.0, | |
| "embedding_layer_norm": false, | |
| "embedding_size": 50304, | |
| "eos_token_id": 50279, | |
| "flash_attention": true, | |
| "include_bias": false, | |
| "init_cutoff_factor": 3.0, | |
| "init_device": "cuda", | |
| "init_fn": "normal", | |
| "init_std": 0.02, | |
| "layer_norm_eps": 1e-06, | |
| "layer_norm_type": "rms", | |
| "layer_norm_with_affine": true, | |
| "max_sequence_length": 2048, | |
| "mlp_hidden_size": null, | |
| "mlp_ratio": 8, | |
| "model_type": "hf_olmo", | |
| "multi_query_attention": null, | |
| "n_heads": 12, | |
| "n_kv_heads": null, | |
| "n_layers": 16, | |
| "norm_after": false, | |
| "pad_token_id": 1, | |
| "precision": "amp_bf16", | |
| "residual_dropout": 0.0, | |
| "rope": true, | |
| "rope_full_precision": true, | |
| "rope_theta": 10000, | |
| "scale_emb_init": false, | |
| "scale_logits": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.50.3", | |
| "use_cache": true, | |
| "vocab_size": 50280, | |
| "weight_tying": false | |
| } | |