Perpetualquest/smolLm2-implementation

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    "hidden_act": "silu",10    "hidden_size": 576,11    "initializer_range": 0.041666666666666664,12    "intermediate_size": 1536,13    "is_llama_config": true,14    "max_position_embeddings": 8192,15    "model_type": "llama",16    "num_attention_heads": 9,17    "num_hidden_layers": 30,18    "num_key_value_heads": 3,19    "pretraining_tp": 1,20    "rms_norm_eps": 1e-05,21    "rope_interleaved": false,22    "rope_scaling": null,23    "rope_theta": 100000,24    "tie_word_embeddings": true,25    "torch_dtype": "bfloat16",26    "transformers_version": "4.40.1",27    "use_cache": true,28    "vocab_size": 4915229  }