You can deploy this model and start earning money today!

RichardErkhov/
firqaaa_-_indo-gemma-2b-alpaca-exl2

Name: firqaaa_-_indo-gemma-2b-alpaca-exl2
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

indo-gemma-2b-alpaca - EXL2

Model creator: https://huggingface.co/firqaaa/
Original model: https://huggingface.co/firqaaa/indo-gemma-2b-alpaca/

Available sizes

Branch	Bits	Description
8_0	8.0	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	Slightly lower quality vs 6.5, but usable
4_25	4.25	GPTQ equivalent bits per weight, slightly higher quality.
3_5	3.5	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/firqaaa_-_indo-gemma-2b-alpaca-exl2 indo-gemma-2b-alpaca-6_5

With huggingface hub:

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch: Linux:

huggingface-cli download firqaaa_-_indo-gemma-2b-alpaca-exl2 --revision 6_5 --local-dir indo-gemma-2b-alpaca-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download firqaaa_-_indo-gemma-2b-alpaca-exl2 --revision 6_5 --local-dir indo-gemma-2b-alpaca-6.5 --local-dir-use-symlinks False

Original model description:

language:

en license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
gemma
trl base_model: unsloth/gemma-2b-bnb-4bit pipeline_tag: text-generation

Description

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.

Context Length

Models are trained on a context length of 8192 tokens.

How to use

python

# Prompt
alpaca_prompt = """Di bawah ini adalah instruksi yang menjelaskan tugas, dipasangkan dengan masukan yang memberikan konteks lebih lanjut. Tulis tanggapan yang melengkapi instruksi dengan tepat.

### Instruksi:
{}

### Masukan:
{}

### Tanggapan:
{}"""

max_seq_length = 4096 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.

if True:
    from unsloth import FastLanguageModel
    model, tokenizer = FastLanguageModel.from_pretrained(
        model_name = "indo-gemma-2b-alpaca",
        max_seq_length = max_seq_length,
        dtype = dtype,
        load_in_4bit = load_in_4bit
    )
    FastLanguageModel.for_inference(model) # Enable native 2x faster inference

inputs = tokenizer(
    [
        alpaca_prompt.format(
            "Sebutkan langkah-langkah membuat nasi goreng!",
            "", # input
            "", # output - leave this blank for generation!
        )
    ], return_tensors = "pt"
).to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 256)

Uploaded model

Developed by: firqaaa
License: apache-2.0
Finetuned from model : unsloth/gemma-2b-bnb-4bit

RichardErkhov/firqaaa_-_indo-gemma-2b-alpaca-exl2