Text Generation
Transformers
Safetensors
llama
model: vicuna
repo_name: vicuna_channel_0_electrical_engineering_Community
file_name: vicuna_channel_0_electrical_engineering_Community_5000_5.pt
pruning_style: channel
community: 0
pruning_ratio: 20
dataset_label: electrical_engineering
sparsity_ratio: 20
['tasksource/mmlu', 'electrical_engineering']
finetune: Community
modules_size: 45
modules: ['12_attn.k', '13_attn.q', '14_mlp.down', '14_mlp.up', '15_attn.v', '16_attn.v', '16_gate', '16_mlp.down', '17_attn.o', '17_attn.q', '17_attn.v', '18_mlp.down', '19_attn.v', '19_gate', '19_mlp.up', '20_attn.q', '20_gate', '20_mlp.up', '21_attn.o', '21_attn.v', '22_attn.k', '22_attn.o', '22_mlp.up', '23_attn.o', '24_attn.o', '25_attn.o', '25_attn.q', '25_mlp.down', '26_attn.v', '26_mlp.down', '26_mlp.up', '27_attn.k', '27_attn.q', '27_mlp.up', '30_attn.q', '3_attn.o', '3_attn.q', '3_mlp.down', '3_mlp.up', '5_gate', '5_mlp.down', '6_attn.q', '7_attn.q', '8_attn.k', '8_attn.q']
rank: 2
tags: ['model: vicuna', 'repo_name: vicuna_channel_0_electrical_engineering_Community', 'file_name: vicuna_channel_0_electrical_engineering_Community_5000_5.pt', 'base_model: lmsys/vicuna-7b-v1.5', 'pruning_style: channel', 'community: 0', 'pruning_ratio: 20', 'dataset_label: electrical_engineering', 'sparsity_ratio: 20', "dataset: ['tasksource/mmlu', 'electrical_engineering']", 'finetune: Community', 'modules_size: 45', "modules: ['12_attn.k', '13_attn.q', '14_mlp.down', '14_mlp.up', '15_attn.v', '16_attn.v', '16_gate', '16_mlp.down', '17_attn.o', '17_attn.q', '17_attn.v', '18_mlp.down', '19_attn.v', '19_gate', '19_mlp.up', '20_attn.q', '20_gate', '20_mlp.up', '21_attn.o', '21_attn.v', '22_attn.k', '22_attn.o', '22_mlp.up', '23_attn.o', '24_attn.o', '25_attn.o', '25_attn.q', '25_mlp.down', '26_attn.v', '26_mlp.down', '26_mlp.up', '27_attn.k', '27_attn.q', '27_mlp.up', '30_attn.q', '3_attn.o', '3_attn.q', '3_mlp.down', '3_mlp.up', '5_gate', '5_mlp.down', '6_attn.q', '7_attn.q', '8_attn.k', '8_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 | |
| } | |