CodeAtCMU/SmolLM2-1.7B-GenerativePerturbations_full_sft_code_data_120K_flowchart

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 0,8  "eos_token_id": 0,9  "head_dim": 64,10  "hidden_act": "silu",11  "hidden_size": 2048,12  "initializer_range": 0.02,13  "intermediate_size": 8192,14  "max_position_embeddings": 8192,15  "mlp_bias": false,16  "model_type": "llama",17  "num_attention_heads": 32,18  "num_hidden_layers": 24,19  "num_key_value_heads": 32,20  "pretraining_tp": 1,21  "rms_norm_eps": 1e-05,22  "rope_scaling": null,23  "rope_theta": 130000,24  "tie_word_embeddings": true,25  "torch_dtype": "bfloat16",26  "transformers_version": "4.51.3",27  "use_cache": false,28  "vocab_size": 4915229}30