| { | |
| "_name_or_path": "Ja-ck/KoMultiGen-General-Llama3-8B", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "neuron": { | |
| "auto_cast_type": "fp16", | |
| "batch_size": 4, | |
| "checkpoint_id": "Ja-ck/KoMultiGen-General-Llama3-8B", | |
| "checkpoint_revision": "b1372a3598cbfa4c66feabe5d975ca8b6c6c82a8", | |
| "compiler_type": "neuronx-cc", | |
| "compiler_version": "2.14.227.0+2d4f85be", | |
| "num_cores": 2, | |
| "sequence_length": 8192, | |
| "task": "text-generation" | |
| }, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 4.0, | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.41.1", | |
| "use_cache": false, | |
| "vocab_size": 128256 | |
| } | |