Text Generation
Transformers
Safetensors
llama
model: llama
repo_name: llama_channel_3_philosophy_Complete Random
file_name: llama_channel_3_philosophy_Complete Random_5000_5.pt
pruning_style: channel
community: 3
pruning_ratio: 20
dataset_label: philosophy
sparsity_ratio: 20
['tasksource/mmlu', 'philosophy']
finetune: Complete Random
modules_size: 30
modules: ['25_gate', '6_mlp.down', '16_mlp.up', '20_attn.v', '3_mlp.up', '5_mlp.up', '15_mlp.down', '24_mlp.down', '18_mlp.down', '22_attn.o', '19_attn.v', '22_attn.q', '14_attn.q', '5_attn.v', '23_mlp.down', '29_attn.v', '9_attn.o', '25_attn.k', '3_mlp.down', '22_gate', '8_attn.k', '27_mlp.down', '7_mlp.down', '27_attn.v', '3_gate', '4_attn.v', '22_attn.k', '23_attn.v', '29_gate', '22_attn.v']
rank: 1
tags: ['model: llama', 'repo_name: llama_channel_3_philosophy_Complete Random', 'file_name: llama_channel_3_philosophy_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-hf', 'pruning_style: channel', 'community: 3', 'pruning_ratio: 20', 'dataset_label: philosophy', 'sparsity_ratio: 20', "dataset: ['tasksource/mmlu', 'philosophy']", 'finetune: Complete Random', 'modules_size: 30', "modules: ['25_gate', '6_mlp.down', '16_mlp.up', '20_attn.v', '3_mlp.up', '5_mlp.up', '15_mlp.down', '24_mlp.down', '18_mlp.down', '22_attn.o', '19_attn.v', '22_attn.q', '14_attn.q', '5_attn.v', '23_mlp.down', '29_attn.v', '9_attn.o', '25_attn.k', '3_mlp.down', '22_gate', '8_attn.k', '27_mlp.down', '7_mlp.down', '27_attn.v', '3_gate', '4_attn.v', '22_attn.k', '23_attn.v', '29_gate', '22_attn.v']", 'rank: 1']
text-generation-inference
| { | |
| "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 | |
| } | |