ModelCloud/TinyLlama-1.1B-Chat-v1.0-dynamic-GPTQ-2024-8-3

# tinyllama 1.1B model has 22 layers
# layer index start at 0

dynamic = {
  # `.*\.` matches the layers_node prefix
  # last 1/2 of the layers 10-21 has 8bit vs 4bit for 0-9
  # last 1/4 of the layers 16-21 has 8bit and group_size 64
  r".*\.(?:1[0-5])\..*": {"bits": 8,}, # match layer 10-15
  r".*\.(?:1[6-9]|20|21)\..*": {"bits": 8, "group_size": 64,}, # match layer 16-21
}