modules: ['12_gate', '7_attn.q', '20_attn.q', '13_attn.o', '8_attn.v', '25_mlp.up', '26_gate', '25_mlp.down', '18_attn.k', '23_gate', '22_mlp.down', '21_gate', '5_gate', '13_mlp.down', '27_mlp.up', '17_mlp.down', '29_mlp.down', '10_mlp.down', '23_mlp.up', '13_attn.q', '5_attn.v', '22_attn.v', '9_gate', '11_attn.o', '5_attn.o', '18_mlp.up', '12_mlp.up', '27_gate', '6_mlp.up', '4_mlp.down', '9_attn.o', '5_mlp.up', '15_mlp.down', '4_mlp.up', '28_gate', '28_attn.o', '12_mlp.down', '7_mlp.down']

rank: 2

tags: ['model: vicuna', 'repo_name: vicuna_block_0_language_identification_Complete Random', 'file_name: vicuna_block_0_language_identification_Complete Random_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: Complete Random', 'modules_size: 38', "modules: ['12_gate', '7_attn.q', '20_attn.q', '13_attn.o', '8_attn.v', '25_mlp.up', '26_gate', '25_mlp.down', '18_attn.k', '23_gate', '22_mlp.down', '21_gate', '5_gate', '13_mlp.down', '27_mlp.up', '17_mlp.down', '29_mlp.down', '10_mlp.down', '23_mlp.up', '13_attn.q', '5_attn.v', '22_attn.v', '9_gate', '11_attn.o', '5_attn.o', '18_mlp.up', '12_mlp.up', '27_gate', '6_mlp.up', '4_mlp.down', '9_attn.o', '5_mlp.up', '15_mlp.down', '4_mlp.up', '28_gate', '28_attn.o', '12_mlp.down', '7_mlp.down']", 'rank: 2']

text-generation-inference

Model card Files Files and versions

xet

Community

vicuna_block_0_language_identification_Complete_Random

File size: 719 Bytes

efbfbc2

{
  "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
}