| { | |
| "alibi_bias": false, | |
| "architectures": [ | |
| "OlmoForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 100257, | |
| "clip_qkv": null, | |
| "eos_token_id": 100257, | |
| "hidden_act": "gelu_new", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "olmo", | |
| "norm_first": true, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 100257, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_scaling_factor": 1.0, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": "transformers.LlamaTokenizerFast", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.1", | |
| "use_cache": true, | |
| "use_rms_norm": true, | |
| "vocab_size": 100352 | |
| } | |