6.6 GB

Ctrl+K

Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 10 layers, 20.5% reduction)

7a6b2a0 verified 2 months ago

.gitattributes

1.57 kB
Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 9 layers, 18.5% reduction) 2 months ago
chat_template.jinja

1.02 kB
Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 9 layers, 18.5% reduction) 2 months ago
config.json

2.57 kB
Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 10 layers, 20.5% reduction) 2 months ago
model.safetensors

6.59 GB
xet

Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 10 layers, 20.5% reduction) 2 months ago
processor_config.json

1.42 kB
Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 9 layers, 18.5% reduction) 2 months ago
pruning_info.json

917 Bytes
Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 10 layers, 20.5% reduction) 2 months ago
tokenizer.json

11.4 MB
xet

Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 9 layers, 18.5% reduction) 2 months ago
tokenizer_config.json

709 Bytes
Layer-pruned Qwen2.5-VL-3B-Instruct (PPL-based (Shortened LLaMA), removed 9 layers, 18.5% reduction) 2 months ago