Downloads · 30 days
12
5% of all-time downloads
WelSSiSKo_v3_llama-2-ko-base_text-generation
Ash-Hun/WelSSiSKo_v3_llama-2-ko-base_text-generation
WelSSiSKo_v3_llama-2-ko-base_text-generation is a text generation model from Ash-Hun. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama2.
<div align='center' <img src="https://cdn-uploads.huggingface.co/production/uploads/6370a4e53d1bd47a4ebc2120/TQSWE0e3dAOKsbb8b5Xd.png" width='45%'/ <h1"WelSSiSKo : Welfare Domain Specific Model"</h1 </div
All-time downloads
242
Public
Repo size
134 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors134 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- llama2
- Access
- Public
- Created
- Feb 11, 2024
- Updated
- Mar 8, 2024
- SHA
- 50164b69
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<div align='center'>
<img src="https://cdn-uploads.huggingface.co/production/uploads/6370a4e53d1bd47a4ebc2120/TQSWE0e3dAO_Ksbb8b5Xd.png" width='45%'/>
<h1>"WelSSiSKo : Welfare Domain Specific Model"</h1>
</div>
Github ▼
If you want to get how to use this model, please check my github repository :)
👉 Github Repo
What is BaseModel ▼
Training procedure ▼
The following bitsandbytes quantization config was used during training:
- load_in_4bit: True
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions ▼
- PEFT 0.8.2.
Evaluate Score
- 적절한 Domain Benchmark Set이 없기때문에 정성평가를 진행하였고 그에 따른 AVG Score는 0.74 입니다.
- Task
- Text Generation
- Library
- peft
- License
- llama2
- Created
- Feb 11, 2024
- Updated
- Mar 8, 2024