54 lines
1.2 KiB
Markdown
54 lines
1.2 KiB
Markdown
---
|
|
license: cc-by-sa-4.0
|
|
---
|
|
|
|
# Join our discord
|
|
[Server Link](https://discord.gg/MrBt3PXdXc)
|
|
|
|
# **License**
|
|
**cc-by-sa-4.0**
|
|
|
|
# **Model Details**
|
|
|
|
**Base Model**
|
|
[maywell/Synatra-7B-v0.3-dpo](https://huggingface.co/maywell/Synatra-7B-v0.3-dpo)
|
|
|
|
**Trained On**
|
|
A100 80GB * 8
|
|
|
|
Sionic AI에서 GPU 자원을 지원받아 제작되었습니다.
|
|
|
|
**Instruction format**
|
|
|
|
It follows **ChatML** format.
|
|
|
|
# **Model Benchmark**
|
|
|
|
TBD
|
|
|
|
# **Implementation Code**
|
|
|
|
Since, chat_template already contains insturction format above.
|
|
You can use the code below.
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
device = "cuda" # the device to load the model onto
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-kiqu-7B")
|
|
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-kiqu-7B")
|
|
|
|
messages = [
|
|
{"role": "user", "content": "사회적 합의는 어떤 맥락에서 사용되는 말이야?"},
|
|
]
|
|
|
|
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
|
|
|
|
model_inputs = encodeds.to(device)
|
|
model.to(device)
|
|
|
|
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
|
|
decoded = tokenizer.batch_decode(generated_ids)
|
|
print(decoded[0])
|
|
``` |