modules: ['12_attn.k', '29_attn.o', '8_attn.k', '3_mlp.down', '7_attn.o', '7_mlp.down', '10_attn.o', '18_mlp.down', '6_attn.q', '21_gate', '20_attn.q', '3_gate', '9_attn.q', '5_mlp.down', '14_mlp.down', '7_gate', '19_gate']

rank: 2

tags: ['model: llama', 'repo_name: llama_channel_4_elementary_math_qa_Complete Random', 'file_name: llama_channel_4_elementary_math_qa_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: channel', 'community: 4', 'pruning_ratio: 20', 'dataset_label: elementary_math_qa', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'elementary_math_qa']", 'finetune: Complete Random', 'modules_size: 17', "modules: ['12_attn.k', '29_attn.o', '8_attn.k', '3_mlp.down', '7_attn.o', '7_mlp.down', '10_attn.o', '18_mlp.down', '6_attn.q', '21_gate', '20_attn.q', '3_gate', '9_attn.q', '5_mlp.down', '14_mlp.down', '7_gate', '19_gate']", 'rank: 2']

text-generation-inference

Model card Files Files and versions

xet

Community

llama_channel_4_elementary_math_qa_Complete_Random

File size: 677 Bytes

32ae9e8

{
  "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
}