Gemma-2-2b-it Fine-Tuned on KoAlpaca-v1.1a
Model Description
This model is a fine-tuned version of the google/gemma-2-2b-it model on the Korean dataset beomi/KoAlpaca-v1.1a. It is designed to generate coherent, contextually appropriate responses in Korean. The fine-tuning process has enhanced the model's ability to handle conversational prompts in a colloquial style, responding with contextually aware and polite expressions.
The base model, Gemma-2-2B-it, is a large pre-trained language model built for multilingual text generation tasks. With the fine-tuning on the KoAlpaca dataset, the model has been optimized to perform better on Korean text generation, offering more natural and conversational outputs.
Training Process
The model was fine-tuned using the KoAlpaca-v1.1a dataset, which is designed for instruction-following tasks in Korean. The dataset contains various examples of questions and corresponding responses in Korean, which helped the model learn polite conversational structures.
Dataset
- Dataset Used: beomi/KoAlpaca-v1.1a
- Type of Data: Instruction-following examples in Korean, with both the instruction and expected response provided in each entry. Training Configuration
- Model Base: google/gemma-2-2b-it
- LoRA Configuration: Applied LoRA with the following parameters:
- Quantization: 4-bit quantization (bnb_4bit) for efficient fine-tuning
- Training Hyperparameters:
- Steps: 3000
- Learning Rate: 2e-4
- Batch Size: 1
- Warmup Steps: 100
- Gradient Accumulation: 4 steps
- Optimizer: paged_adamw_8bit
- Precision: FP16
Results and Performance
Example Input: βλ°°κ° κ³ νμ λ§λΌνμ λ¨Ήμμ΄μ.β (I was feeling hungry, so I ate maratang.)
Before Fine-tuning: Output:βλ§λΌν (maratang): This is a Korean soup made with various ingredients like meat, vegetables, and noodles.
κ³ ν (gopa): This means βto be hungry.β
λ¨Ήμμ΄μ (meok-eosseoyo): This is the polite way to say βI ate.ββAfter Fine-tuning: Output: βλ§μκ² λμ ¨κ΅°μ! μ λ μ΄λ κ² νλ©΄ μ’κ² μ΅λλ€. λ΄μΌμ μ΄λ€ μμμ ν΄λ³ΌκΉ μκ°ν΄λ³΄μΈμ?β (It sounds like you enjoyed your meal! I should try that too. What do you plan to cook tomorrow?)
The fine-tuned model shows a significant improvement in contextual understanding and produces more conversational and polite responses in Korean. It also demonstrates an ability to provide helpful follow-up suggestions, which is essential in conversational agents.
Future Work
- Further fine-tuning on larger or more diverse Korean datasets could improve the model's versatility.
- Exploring different LoRA configurations and quantization techniques could yield more efficient results for deployment on smaller devices.
- Evaluation with human raters to measure improvements in conversation quality.
- Downloads last month
- 10