{ "_name_or_path": "TeeZee/NEBULA_3rd_SFT_slimorca_1_epoch_50k", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 4096, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 108, "num_key_value_heads": 8, "pad_token_id": 2, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.0", "unsloth_version": "2024.4", "use_cache": false, "vocab_size": 32000, "quantization_config": { "quant_method": "exl2", "version": "0.0.20", "bits": 4.45, "head_bits": 8, "calibration": { "rows": 100, "length": 2048, "dataset": "wikitext-103-v1_wikitext-test.parquet" } } }