| { |
| "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, |
| "auto_map": { |
| "AutoConfig": "configuration_olmo.OLMoConfig", |
| "AutoModelForCausalLM": "modeling_olmo.OLMoForCausalLM", |
| "AutoTokenizer": [ |
| "tokenization_olmo_fast.OLMoTokenizerFast", |
| "tokenization_olmo_fast.OLMoTokenizerFast" |
| ] |
| }, |
| "bias_for_layer_norm": false, |
| "block_group_size": 1, |
| "block_type": "sequential", |
| "d_model": 4096, |
| "embedding_dropout": 0.0, |
| "embedding_size": 50304, |
| "eos_token_id": 50279, |
| "flash_attention": true, |
| "include_bias": false, |
| "init_cutoff_factor": null, |
| "init_device": "meta", |
| "init_fn": "mitchell", |
| "init_std": 0.02, |
| "layer_norm_type": "default", |
| "layer_norm_with_affine": false, |
| "max_sequence_length": 2048, |
| "mlp_hidden_size": 22016, |
| "mlp_ratio": 4, |
| "model_type": "hf_olmo", |
| "multi_query_attention": false, |
| "n_heads": 32, |
| "n_layers": 32, |
| "pad_token_id": 1, |
| "precision": "amp_bf16", |
| "residual_dropout": 0.0, |
| "rope": true, |
| "rope_full_precision": true, |
| "scale_logits": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.35.0.dev0", |
| "use_cache": true, |
| "vocab_size": 50280, |
| "weight_tying": false |
| } |
|
|
