| { |
| "_name_or_path": "/home/alialkaswan/scratch/mem-quant/training/mellum4b/epochs/checkpoint-3332", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "eos_token_id": 0, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 3072, |
| "initializer_range": 0.02, |
| "intermediate_size": 8256, |
| "max_position_embeddings": 8192, |
| "max_sequence_length": 8192, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 24, |
| "num_hidden_layers": 30, |
| "num_key_value_heads": 24, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.46.3", |
| "use_cache": true, |
| "vocab_size": 98304 |
| } |
|
|
