ssgplabon/CodeParrotFT-MyDataset

1{2  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "head_dim": 64,11  "hidden_act": "silu",12  "hidden_size": 576,13  "initializer_range": 0.041666666666666664,14  "intermediate_size": 1536,15  "is_llama_config": true,16  "max_position_embeddings": 8192,17  "mlp_bias": false,18  "model_type": "llama",19  "num_attention_heads": 9,20  "num_hidden_layers": 30,21  "num_key_value_heads": 3,22  "pad_token_id": 2,23  "pretraining_tp": 1,24  "rms_norm_eps": 1e-05,25  "rope_interleaved": false,26  "rope_scaling": null,27  "rope_theta": 100000,28  "tie_word_embeddings": true,29  "torch_dtype": "float32",30  "transformers_version": "4.47.1",31  "use_cache": true,32  "vocab_size": 4915233}34