modules: ['26_attn.v', '28_gate', '8_mlp.down', '9_mlp.up', '30_attn.q', '10_mlp.down', '30_mlp.down', '28_mlp.up', '12_attn.k', '16_gate', '14_attn.v', '16_attn.v', '12_mlp.down', '20_mlp.up', '11_mlp.down', '14_attn.q', '24_mlp.down', '17_mlp.up', '7_mlp.down', '4_attn.k', '5_attn.o', '3_attn.v', '22_mlp.down', '30_attn.v', '21_attn.o', '29_attn.k', '6_mlp.up', '23_attn.k', '29_mlp.up', '28_attn.v', '22_mlp.up', '14_attn.o', '5_mlp.up']

rank: 1

tags: ['model: llama_chat', 'repo_name: llama_chat_block_2_abstract_narrative_understanding_Complete Random', 'file_name: llama_chat_block_2_abstract_narrative_understanding_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: block', 'community: 2', 'pruning_ratio: 20', 'dataset_label: abstract_narrative_understanding', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'abstract_narrative_understanding']", 'finetune: Complete Random', 'modules_size: 33', "modules: ['26_attn.v', '28_gate', '8_mlp.down', '9_mlp.up', '30_attn.q', '10_mlp.down', '30_mlp.down', '28_mlp.up', '12_attn.k', '16_gate', '14_attn.v', '16_attn.v', '12_mlp.down', '20_mlp.up', '11_mlp.down', '14_attn.q', '24_mlp.down', '17_mlp.up', '7_mlp.down', '4_attn.k', '5_attn.o', '3_attn.v', '22_mlp.down', '30_attn.v', '21_attn.o', '29_attn.k', '6_mlp.up', '23_attn.k', '29_mlp.up', '28_attn.v', '22_mlp.up', '14_attn.o', '5_mlp.up']", 'rank: 1']

text-generation-inference

Model card Files Files and versions Community

llama_chat_block_2_abstract_narrative_understanding_Complete_Random

File size: 677 Bytes

4a0f79c

{
  "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
}