Fast-Inference with Ctranslate2

Speedup inference by 2x-8x using int8 inference in C++

quantized version of databricks/dolly-v2-12b

pip install hf_hub_ctranslate2>=1.0.0 ctranslate2>=3.13.0

Checkpoint compatible to ctranslate2 and hf-hub-ctranslate2

compute_type=int8_float16 for device="cuda"
compute_type=int8 for device="cpu"

from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub

model_name = "michaelfeil/ct2fast-dolly-v2-12b"
model = GeneratorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name, 
        device="cuda",
        compute_type="int8_float16"
)
outputs = model.generate(
    text=["How do you call a fast Flan-ingo?", "User: How are you doing?"],
)
print(outputs)

Licence and other remarks:

This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

Usage of Dolly-v2:

According to the Intruction Pipeline of databricks/dolly-v2-12b

# from https://huggingface.co/databricks/dolly-v2-12b
def encode_prompt(instruction):
  INSTRUCTION_KEY = "### Instruction:"
  RESPONSE_KEY = "### Response:"
  END_KEY = "### End"
  INTRO_BLURB = (
      "Below is an instruction that describes a task. Write a response that appropriately completes the request."
  )
  
  # This is the prompt that is used for generating responses using an already trained model.  It ends with the response
  # key, where the job of the model is to provide the completion that follows it (i.e. the response itself).
  PROMPT_FOR_GENERATION_FORMAT = """{intro}
  {instruction_key}
  {instruction}
  {response_key}
  """.format(
      intro=INTRO_BLURB,
      instruction_key=INSTRUCTION_KEY,
      instruction="{instruction}",
      response_key=RESPONSE_KEY,
  )
  return PROMPT_FOR_GENERATION_FORMAT.format(instruction=instruction)