Q-bert/ChessLlama

1{2  "_name_or_path": "Q-bert/ChessLlamaV2",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 0,9  "eos_token_id": 1,10  "hidden_act": "silu",11  "hidden_size": 512,12  "initializer_range": 0.02,13  "intermediate_size": 11008,14  "max_position_embeddings": 2048,15  "mlp_bias": false,16  "model_type": "llama",17  "num_attention_heads": 16,18  "num_hidden_layers": 8,19  "num_key_value_heads": 4,20  "pad_token_id": 0,21  "pretraining_tp": 1,22  "rms_norm_eps": 1e-06,23  "rope_scaling": null,24  "rope_theta": 10000.0,25  "tie_word_embeddings": false,26  "torch_dtype": "float32",27  "transformers_version": "4.42.4",28  "use_cache": true,29  "vocab_size": 201030}31