{ "_name_or_path": "ankner/smol-360m", "architectures": [ "RewardModel" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "eos_token_id": 0, "head_dim": 64, "hidden_act": "silu", "hidden_size": 960, "initializer_range": 0.02, "intermediate_size": 2560, "max_position_embeddings": 2048, "mean": 0.4086643159389496, "mlp_bias": false, "model_type": "llama", "normalize_reward": false, "num_attention_heads": 15, "num_hidden_layers": 32, "num_key_value_heads": 5, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "std": 0.7583338618278503, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.46.3", "use_cache": false, "value_head_prefix": "score", "vocab_size": 49152 }