Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_channel_0_evaluating_information_essentiality_Complete Random
file_name: vicuna_channel_0_evaluating_information_essentiality_Complete Random_5000_5.pt
pruning_style: channel
community: 0
pruning_ratio: 20
dataset_label: evaluating_information_essentiality
sparsity_ratio: 20
['tasksource/bigbench', 'evaluating_information_essentiality']
finetune: Complete Random
modules_size: 45
modules: ['30_mlp.up', '3_attn.k', '12_gate', '27_attn.v', '30_gate', '7_attn.k', '9_attn.o', '15_attn.k', '7_attn.v', '5_attn.q', '11_gate', '14_attn.k', '6_attn.v', '11_attn.q', '8_attn.v', '15_attn.o', '13_attn.o', '18_gate', '24_mlp.up', '30_attn.v', '9_mlp.down', '8_mlp.up', '11_mlp.up', '18_attn.q', '16_mlp.up', '21_mlp.down', '19_mlp.down', '3_attn.v', '22_attn.q', '23_mlp.up', '19_attn.k', '10_attn.v', '27_attn.o', '29_mlp.down', '25_mlp.up', '23_attn.q', '15_mlp.down', '12_attn.v', '26_attn.q', '6_attn.o', '24_mlp.down', '21_gate', '13_gate', '10_mlp.up', '28_attn.v']
rank: 1
tags: ['model: vicuna', 'repo_name: vicuna_channel_0_evaluating_information_essentiality_Complete Random', 'file_name: vicuna_channel_0_evaluating_information_essentiality_Complete Random_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: channel', 'community: 0', 'pruning_ratio: 20', 'dataset_label: evaluating_information_essentiality', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'evaluating_information_essentiality']", 'finetune: Complete Random', 'modules_size: 45', "modules: ['30_mlp.up', '3_attn.k', '12_gate', '27_attn.v', '30_gate', '7_attn.k', '9_attn.o', '15_attn.k', '7_attn.v', '5_attn.q', '11_gate', '14_attn.k', '6_attn.v', '11_attn.q', '8_attn.v', '15_attn.o', '13_attn.o', '18_gate', '24_mlp.up', '30_attn.v', '9_mlp.down', '8_mlp.up', '11_mlp.up', '18_attn.q', '16_mlp.up', '21_mlp.down', '19_mlp.down', '3_attn.v', '22_attn.q', '23_mlp.up', '19_attn.k', '10_attn.v', '27_attn.o', '29_mlp.down', '25_mlp.up', '23_attn.q', '15_mlp.down', '12_attn.v', '26_attn.q', '6_attn.o', '24_mlp.down', '21_gate', '13_gate', '10_mlp.up', '28_attn.v']", 'rank: 1']
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 | |
| } | |