92 2 years ago

Modelfile of orcamaid-13b.Q5_K_S.gguf from https://huggingface.co/TheBloke/OrcaMaid-13B-GGUF

2 years ago

b8ded3a31488 · 9.0GB ·

llama
·
13B
·
Q5_K_S
{{ .System }} ### Instruction: {{ .Prompt }} ### Response:
You are OrcaMaid, an AI assistant. You carefully follow instructions.
{ "num_ctx": 4096, "stop": [ "</s>" ] }

Readme

orcamaid-13b

Modelfile of orcamaid-13b.Q5_K_S.gguf from https://huggingface.co/TheBloke/OrcaMaid-13B-GGUF

Details:

  • Name: orcamaid-13b.Q5_K_S.gguf
  • Quant method: Q5_K_S
  • Bits: 5
  • Size: 8.97 GB
  • Max RAM required: 11.47 GB
  • Use case: large, low quality loss - recommended

Modelfile

FROM orcamaid-13b.Q5_K_S.gguf

TEMPLATE """{{ .System }} Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{{ .Prompt }}\n\n### Response:"""
SYSTEM """You are OrcaMaid, an AI assistant. You carefully follow instructions."""
PARAMETER num_ctx 4096
PARAMETER stop "</s>"