{ "_name_or_path": "/storage/dylan/popai/deepseek-ai/deepseek-coder-6.7b-base/models/synthesis/deepseek-ai/deepseek-coder-6.7b-base/prompted/repair/repair-use_context-use_nearest_examples-true-synthetic-split1-50-LR-1.5e-5-epochs-1-no-draft-use-error-message-highlighted_error-max_instances--1/merged/checkpoint-2440", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 32013, "eos_token_id": 32014, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": { "factor": 4.0, "type": "linear" }, "rope_theta": 100000, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.41.2", "use_cache": true, "vocab_size": 32022 }