{ "architectures": [ "Starcoder2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 50256, "dtype": "bfloat16", "embedding_dropout": 0.0, "eos_token_id": 50256, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 384, "initializer_range": 0.018042, "intermediate_size": 1024, "max_position_embeddings": 2048, "model_type": "starcoder2", "norm_epsilon": 1e-05, "num_attention_heads": 6, "num_hidden_layers": 6, "num_key_value_heads": 2, "pad_token_id": null, "residual_dropout": 0.0, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "sliding_window": 4096, "tie_word_embeddings": false, "transformers_version": "5.5.0", "use_bias": true, "use_cache": false, "vocab_size": 49152 }