Downloads · 30 days
11
0% of all-time downloads
Mistral-7b-ko-Y24-DPO_v0.1
AIdenU/Mistral-7b-ko-Y24-DPO_v0.1
Mistral-7b-ko-Y24-DPO_v0.1 is a text generation model from AIdenU. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
38.1K
Public
Repo size
29 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin14.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- mistral
- Access
- Public
- Created
- Dec 21, 2023
- Updated
- Dec 21, 2023
- SHA
- 78813fb5
Model card
From the Hugging Face model README
Model Generation
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("AidenU/Mistral-7b-ko-Y24-DPO_v0.1", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("AidenU/Mistral-7b-ko-Y24-DPO_v0.1")
messages = [
{"role":"user", "content", "안녕하세요?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
inputs = encodeds.to("cuda")
model.to("cuda")
outputs = model.generated(
inputs,
max_new_tokens=256,
do_sample=True
)
decoded = tokenizer.batch_decode(outputs)
print(decoded[0])
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- Languages
- ko
- Created
- Dec 21, 2023
- Updated
- Dec 21, 2023