| { |
| "_name_or_path": "mock_training_run/llama_configs/config.json", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 1536, |
| "initializer_range": 0.02, |
| "intermediate_size": 4128, |
| "max_position_embeddings": 2048, |
| "model_type": "llama", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 12, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.34.1", |
| "use_cache": true, |
| "use_flash_attention_2": true, |
| "vocab_size": 32000 |
| } |
|
|
