Text Generation
Transformers
Safetensors
llama
model: llama_chat
repo_name: llama_chat_block_2_abstract_narrative_understanding_Community
file_name: llama_chat_block_2_abstract_narrative_understanding_Community_5000_5.pt
pruning_style: block
community: 2
pruning_ratio: 20
dataset_label: abstract_narrative_understanding
sparsity_ratio: 20
['tasksource/bigbench', 'abstract_narrative_understanding']
finetune: Community
modules_size: 33
modules: ['10_attn.q', '10_attn.v', '12_attn.o', '13_attn.q', '13_attn.v', '14_attn.k', '15_attn.k', '15_attn.v', '16_attn.o', '17_attn.o', '17_attn.q', '17_attn.v', '18_attn.k', '18_attn.q', '20_attn.v', '21_attn.k', '21_attn.v', '22_attn.v', '23_attn.v', '24_attn.k', '24_attn.o', '24_attn.q', '26_attn.k', '27_attn.o', '28_attn.q', '30_attn.o', '3_attn.k', '4_attn.o', '4_attn.v', '7_attn.q', '7_attn.v', '8_attn.k', '9_attn.k']
rank: 1
tags: ['model: llama_chat', 'repo_name: llama_chat_block_2_abstract_narrative_understanding_Community', 'file_name: llama_chat_block_2_abstract_narrative_understanding_Community_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: Community', 'modules_size: 33', "modules: ['10_attn.q', '10_attn.v', '12_attn.o', '13_attn.q', '13_attn.v', '14_attn.k', '15_attn.k', '15_attn.v', '16_attn.o', '17_attn.o', '17_attn.q', '17_attn.v', '18_attn.k', '18_attn.q', '20_attn.v', '21_attn.k', '21_attn.v', '22_attn.v', '23_attn.v', '24_attn.k', '24_attn.o', '24_attn.q', '26_attn.k', '27_attn.o', '28_attn.q', '30_attn.o', '3_attn.k', '4_attn.o', '4_attn.v', '7_attn.q', '7_attn.v', '8_attn.k', '9_attn.k']", '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 | |
| } | |