Modelpublic

OpenWeightsAI/Vynis-0.2-8B-Instant

sourceHugging Faceapache-2.0updated 7d agoView on Hugging Face

0likes

Model Card

GPLM-0.2-8B-Instant

GPLM-0.2-8B-Instant is an instruction-tuned language model based on Qwen2.5-7B-Instruct.

Model Details

—Model: GPLM-0.2-8B-Instant
—Base Model: unsloth/Qwen2.5-7B-Instruct
—Architecture: Qwen2
—Parameters: ~8B
—Library: Transformers
—License: Apache 2.0

Training Data

The model was fine-tuned using:

—yahma/alpaca-cleaned
—CohereLabs/aya_dataset

Intended Use

GPLM-0.2-8B-Instant is intended for:

—General question answering
—Instruction following
—Arabic and English text generation
—General conversational tasks
—Programming and technical assistance

Limitations

The model may generate incorrect, outdated, or misleading information. Generated content should be reviewed before being used in important or safety-critical applications.

Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "OpenWeightsAI/gplm-0.2-8B-instant"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)