| { | |
| "_name_or_path": "/home/damian/.cache/huggingface/hub/models--neuralmagic--llama2.c-stories110M-pruned50/snapshots/ae99c0a865dc99a60311e3fd3fc145eb339cff77", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "max_position_embeddings": 1024, | |
| "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, | |
| "sparsity_config": { | |
| "format": "sparse_bitmask", | |
| "global_sparsity": 38.77294698534069, | |
| "sparsity_structure": "0:0" | |
| }, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.3", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } |