| { | |
| "_name_or_path": "./my_llama3.2_1b_llama_sample10000/checkpoint-771", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "drop_attention_mask": false, | |
| "eos_token_id": 128001, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "mask_input": false, | |
| "mask_rate": 0, | |
| "max_position_embeddings": 131072, | |
| "mixup": false, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "neft_all_token": false, | |
| "neftune_alpha": 0, | |
| "not_mask_source": true, | |
| "not_mask_tgt": false, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "only_drop_target": false, | |
| "pretraining_tp": 1, | |
| "replace": false, | |
| "replace_rate": 0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "token_dropout": 0, | |
| "token_noise": false, | |
| "token_noise_hard": false, | |
| "token_noise_random": false, | |
| "token_noise_sample": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "use_cache": true, | |
| "vocab_size": 128259 | |
| } | |