| { |
| "_name_or_path": "/home/projects/polyullm/congkai/nemo_experiments/llama32_1B_mix_decay_2_33440_dec_mmlu_code_sft_stem_n4_l1.4e-4_s42_bs2048/2025-02-14_23-36-47/checkpoints/nemo_llama32_1B--val_loss=0.98-step=6999-consumed_samples=14336000.0/context/Llama-3.2-1B", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "eos_token_id": 128001, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 8192, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 16, |
| "num_key_value_heads": 8, |
| "pretraining_tp": 1, |
| "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, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.45.2", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
