Text Generation
Transformers
Safetensors
llama
model: llama_chat
repo_name: llama_chat_channel_3_sentence_ambiguity_Complete Random
file_name: llama_chat_channel_3_sentence_ambiguity_Complete Random_5000_5.pt
pruning_style: channel
community: 3
pruning_ratio: 20
dataset_label: sentence_ambiguity
sparsity_ratio: 20
['tasksource/bigbench', 'sentence_ambiguity']
finetune: Complete Random
modules_size: 53
modules: ['25_attn.q', '17_attn.q', '17_attn.k', '22_attn.o', '7_mlp.down', '28_attn.q', '7_attn.k', '5_mlp.down', '3_attn.k', '14_mlp.down', '3_attn.o', '25_gate', '15_attn.v', '23_attn.q', '12_gate', '13_mlp.up', '24_attn.q', '3_attn.v', '27_attn.v', '14_mlp.up', '18_attn.v', '29_attn.q', '30_mlp.down', '25_attn.v', '22_gate', '17_attn.o', '23_attn.k', '5_mlp.up', '28_attn.o', '21_attn.q', '12_attn.o', '28_attn.k', '28_gate', '27_attn.o', '8_gate', '15_attn.q', '10_gate', '3_mlp.up', '8_attn.o', '7_attn.q', '6_attn.o', '30_gate', '16_attn.v', '23_gate', '23_mlp.down', '27_gate', '15_attn.k', '15_gate', '23_mlp.up', '29_attn.o', '26_attn.v', '7_mlp.up', '12_mlp.down']
rank: 2
tags: ['model: llama_chat', 'repo_name: llama_chat_channel_3_sentence_ambiguity_Complete Random', 'file_name: llama_chat_channel_3_sentence_ambiguity_Complete Random_5000_5.pt', 'base_model: meta-llama/Llama-2-7b-chat-hf', 'pruning_style: channel', 'community: 3', 'pruning_ratio: 20', 'dataset_label: sentence_ambiguity', 'sparsity_ratio: 20', "dataset: ['tasksource/bigbench', 'sentence_ambiguity']", 'finetune: Complete Random', 'modules_size: 53', "modules: ['25_attn.q', '17_attn.q', '17_attn.k', '22_attn.o', '7_mlp.down', '28_attn.q', '7_attn.k', '5_mlp.down', '3_attn.k', '14_mlp.down', '3_attn.o', '25_gate', '15_attn.v', '23_attn.q', '12_gate', '13_mlp.up', '24_attn.q', '3_attn.v', '27_attn.v', '14_mlp.up', '18_attn.v', '29_attn.q', '30_mlp.down', '25_attn.v', '22_gate', '17_attn.o', '23_attn.k', '5_mlp.up', '28_attn.o', '21_attn.q', '12_attn.o', '28_attn.k', '28_gate', '27_attn.o', '8_gate', '15_attn.q', '10_gate', '3_mlp.up', '8_attn.o', '7_attn.q', '6_attn.o', '30_gate', '16_attn.v', '23_gate', '23_mlp.down', '27_gate', '15_attn.k', '15_gate', '23_mlp.up', '29_attn.o', '26_attn.v', '7_mlp.up', '12_mlp.down']", 'rank: 2']
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 | |
| } | |