| { | |
| "_name_or_path": "/scratch/fsalerno/mem-tune/training/20ktraining/scoder7b/epochs/checkpoint-1666", | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "Starcoder2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "attention_softmax_in_fp32": true, | |
| "bos_token_id": 0, | |
| "embedding_dropout": 0.1, | |
| "eos_token_id": 0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 4608, | |
| "initializer_range": 0.018042, | |
| "intermediate_size": 18432, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 16384, | |
| "mlp_type": "default", | |
| "model_type": "starcoder2", | |
| "norm_epsilon": 1e-05, | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 36, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 4, | |
| "residual_dropout": 0.1, | |
| "rope_theta": 1000000, | |
| "scale_attention_softmax_in_fp32": true, | |
| "scale_attn_weights": true, | |
| "sliding_window": 4096, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.1", | |
| "use_bias": true, | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| } | |