RichardErkhov/frankenmerger_-_gemma-4b-instruct-v0.1-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-4b-instruct-v0.1 - AWQ

• Model creator: https://huggingface.co/frankenmerger/
• Original model: https://huggingface.co/frankenmerger/gemma-4b-instruct-v0.1/

Original model description:

widget: - text: Who is Alan Turing? example_title: Person - text: What is Aurora Borealis? example_title: Question license: apache-2.0 language: - en pipeline_tag: text-generation

gemoy-4B-instruct is frankenmerge from gemma-2b-it.

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "frankenmerger/gemma-4b-instruct-v0.1"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])