|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- millat/StudyAbroadGPT-Dataset |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- unsloth/mistral-7b-instruct-v0.3-bnb-4bit |
|
|
tags: |
|
|
- unsloth |
|
|
- trl |
|
|
- sft |
|
|
--- |
|
|
# StudyAbroadGPT-7B |
|
|
|
|
|
A fine-tuned version of Mistral-7B optimized for study abroad assistance. |
|
|
|
|
|
## Model Details |
|
|
- Base Model: Mistral-7B |
|
|
- Training: LoRA fine-tuning (r=16, alpha=32) |
|
|
- Quantization: 4-bit |
|
|
- Max Length: 2048 tokens |
|
|
|
|
|
## Usage |
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("millat/StudyAbroadGPT-7B") |
|
|
tokenizer = AutoTokenizer.from_pretrained("millat/StudyAbroadGPT-7B") |
|
|
``` |
