---
language:
- ko
pipeline_tag: text-generation
tags:
- finetune
---
# Model Card for mistral-ko-7b-tech
It is a fine-tuned model using Korean and NEFT in the mistral-7b model.

## Model Details

* **Model Developers** :  shleeeee(Seunghyeon Lee)
* **Repository** : To be added
* **Model Architecture** : The mistral-ko-7b-wiki-neft is is a fine-tuned version of the Mistral-7B-v0.1.
* **Lora target modules** : q_proj, k_proj, v_proj, o_proj,gate_proj
* **train_batch** : 4
* **Max_step** : 500

## Dataset
Korean Custom Dataset

## Prompt template: Mistral
```
<s>[INST]{['instruction']}[/INST]{['output']}</s>
```

## Usage
``` 
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shleeeee/mistral-ko-7b-tech")
model = AutoModelForCausalLM.from_pretrained("shleeeee/mistral-ko-7b-tech")

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="shleeeee/mistral-ko-7b-tech")
```

## Evaluation
![image/png](https://cdn-uploads.huggingface.co/production/uploads/654495fa893aec5da96e9134/6z75dYa8TdTy4Y7EIl0CK.png)