modules: ['4_mlp.down', '15_attn.q', '18_attn.k', '30_mlp.up', '8_gate', '6_attn.v', '26_attn.q', '12_attn.k', '30_attn.q', '20_mlp.up', '23_attn.k', '23_attn.v', '30_attn.v', '11_mlp.down', '25_gate', '17_attn.q', '29_attn.q']

rank: 1

tags: ['model: llama', 'repo_name: llama_channel_4_date_understanding_Complete Random', 'file_name: llama_channel_4_date_understanding_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: channel', 'community: 4', 'pruning_ratio: 20', 'dataset_label: date_understanding', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'date_understanding']", 'finetune: Complete Random', 'modules_size: 17', "modules: ['4_mlp.down', '15_attn.q', '18_attn.k', '30_mlp.up', '8_gate', '6_attn.v', '26_attn.q', '12_attn.k', '30_attn.q', '20_mlp.up', '23_attn.k', '23_attn.v', '30_attn.v', '11_mlp.down', '25_gate', '17_attn.q', '29_attn.q']", 'rank: 1']

text-generation-inference

Model card Files Files and versions Community

llama_channel_4_date_understanding_Complete_Random

File size: 677 Bytes

01237ba

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "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,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.52.4",
  "use_cache": true,
  "vocab_size": 32000
}