| { | |
| "_name_or_path": "/home/rahul/.cache/huggingface/hub/models--Xenova--llama2.c-stories15M/snapshots/ccdd47c2dc554aeecd2bb4e713e1c988f206a296", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 48, | |
| "hidden_act": "silu", | |
| "hidden_size": 288, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 768, | |
| "max_position_embeddings": 256, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 6, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 6, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "quant_method": "compressed-tensors", | |
| "sparsity_config": { | |
| "format": "dense", | |
| "global_sparsity": 0.12233772669884009, | |
| "ignore": [ | |
| "lm_head" | |
| ], | |
| "registry_requires_subclass": false, | |
| "sparsity_structure": "2:4", | |
| "targets": [ | |
| "Linear" | |
| ] | |
| }, | |
| "version": "0.7.1" | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.45.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } |