Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_block_0_language_identification_All
file_name: vicuna_block_0_language_identification_All_5000_5.pt
pruning_style: block
community: 0
pruning_ratio: 20
dataset_label: language_identification
sparsity_ratio: 20
['tasksource/bigbench', 'language_identification']
finetune: All
modules_size: 38
modules: ['10_attn.k', '10_attn.v', '11_attn.k', '11_attn.q', '11_attn.v', '13_attn.k', '14_attn.k', '14_attn.o', '14_attn.q', '17_attn.o', '18_attn.q', '19_attn.o', '20_attn.k', '20_attn.v', '21_attn.v', '22_attn.k', '23_attn.o', '24_attn.k', '24_attn.v', '25_attn.o', '25_attn.v', '27_attn.k', '27_attn.v', '28_attn.k', '28_attn.q', '29_attn.k', '29_attn.o', '29_attn.v', '30_attn.k', '30_attn.q', '3_attn.k', '3_attn.q', '4_attn.k', '4_attn.q', '4_attn.v', '6_attn.k', '6_attn.v', '9_attn.q']
rank: 2
tags: ['model: vicuna', 'repo_name: vicuna_block_0_language_identification_All', 'file_name: vicuna_block_0_language_identification_All_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: block', 'community: 0', 'pruning_ratio: 20', 'dataset_label: language_identification', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'language_identification']", 'finetune: All', 'modules_size: 38', "modules: ['10_attn.k', '10_attn.v', '11_attn.k', '11_attn.q', '11_attn.v', '13_attn.k', '14_attn.k', '14_attn.o', '14_attn.q', '17_attn.o', '18_attn.q', '19_attn.o', '20_attn.k', '20_attn.v', '21_attn.v', '22_attn.k', '23_attn.o', '24_attn.k', '24_attn.v', '25_attn.o', '25_attn.v', '27_attn.k', '27_attn.v', '28_attn.k', '28_attn.q', '29_attn.k', '29_attn.o', '29_attn.v', '30_attn.k', '30_attn.q', '3_attn.k', '3_attn.q', '4_attn.k', '4_attn.q', '4_attn.v', '6_attn.k', '6_attn.v', '9_attn.q']", 'rank: 2']
text-generation-inference
| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "do_sample": null, | |
| "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, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.52.4", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |