| { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "katuni4ka/tiny-random-olmo-hf", | |
| "architectures": [ | |
| "OlmoForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "clip_qkv": null, | |
| "eos_token_id": 0, | |
| "hidden_act": "silu", | |
| "hidden_size": 64, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 172, | |
| "max_position_embeddings": 2048, | |
| "model_type": "olmo", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 1, | |
| "pretraining_tp": 1, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.0", | |
| "use_cache": false, | |
| "vocab_size": 50304 | |
| } | |