Text Generation
Transformers
Safetensors
llama
model: llama_chat
repo_name: llama_chat_block_1_discourse_marker_prediction_Community
file_name: llama_chat_block_1_discourse_marker_prediction_Community_5000_5.pt
pruning_style: block
community: 1
pruning_ratio: 20
dataset_label: discourse_marker_prediction
sparsity_ratio: 20
['tasksource/bigbench', 'discourse_marker_prediction']
finetune: Community
modules_size: 20
modules: ['10_attn.k', '13_attn.o', '14_attn.q', '14_attn.v', '16_attn.v', '17_attn.k', '19_attn.v', '20_attn.k', '21_attn.q', '23_attn.k', '25_attn.o', '26_attn.v', '28_attn.v', '30_attn.k', '4_attn.q', '5_attn.o', '6_attn.o', '7_attn.k', '9_attn.q', '9_attn.v']
rank: 1
tags: ['model: llama_chat', 'repo_name: llama_chat_block_1_discourse_marker_prediction_Community', 'file_name: llama_chat_block_1_discourse_marker_prediction_Community_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: block', 'community: 1', 'pruning_ratio: 20', 'dataset_label: discourse_marker_prediction', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'discourse_marker_prediction']", 'finetune: Community', 'modules_size: 20', "modules: ['10_attn.k', '13_attn.o', '14_attn.q', '14_attn.v', '16_attn.v', '17_attn.k', '19_attn.v', '20_attn.k', '21_attn.q', '23_attn.k', '25_attn.o', '26_attn.v', '28_attn.v', '30_attn.k', '4_attn.q', '5_attn.o', '6_attn.o', '7_attn.k', '9_attn.q', '9_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 | |
| } | |