| { | |
| "_name_or_path": "mnt/data/jhkim/spdp/spdp/wanda/out/llama2_7b/unstructured/wanda0.1-spdp", | |
| "architectures": [ | |
| "LlamaSparseForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoModel": "transformers.models.llama.modeling_llama_sparse.LlamaSparseModel", | |
| "AutoModelForCausalLM": "transformers.models.llama.modeling_llama_sparse.LlamaSparseForCausalLM", | |
| "AutoModelForQuestionAnswering": "transformers.models.llama.modeling_llama_sparse.LlamaSparseForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "transformers.models.llama.modeling_llama_sparse.LlamaSparseForSequenceClassification", | |
| "AutoModelForTokenClassification": "transformers.models.llama.modeling_llama_sparse.LlamaSparseForTokenClassification" | |
| }, | |
| "bos_token_id": 1, | |
| "dtype": "float16", | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "spdp_format": "sparse", | |
| "spdp_model_class": "LlamaSparseForCausalLM", | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.56.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |