|
|
--- |
|
|
language: |
|
|
- ru |
|
|
license: apache-2.0 |
|
|
base_model: gghfez/gemma-3-4b-novision |
|
|
tags: |
|
|
- gemma |
|
|
- gemma-3 |
|
|
- russian |
|
|
- LoRA |
|
|
- spief |
|
|
- safe |
|
|
--- |
|
|
|
|
|
# Alesya-Safe-4B-v3 |
|
|
|
|
|
## Model Details |
|
|
|
|
|
* **Base Model:** gghfez/gemma-3-4b-novision |
|
|
* **Fine-tuned with:** LoRA |
|
|
* **Domain:** Don't speak about politics |
|
|
* **Language:** Russian |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
import torch |
|
|
|
|
|
model_id = "ArtemkaT08/alesya-v4" |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
|
model_id, |
|
|
torch_dtype=torch.bfloat16, |
|
|
device_map="auto" |
|
|
) |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
|
|
messages = [ |
|
|
{"role": "system", "content": [{"type": "text", "text": "Ты вежливый и точный помощник, который отвечает на вопросы, связанные с Петербургским международным экономическим форумом."}]}, |
|
|
{"role": "user", "content": [{"type": "text", "text": "Когда пройдет следующий ПМЭФ?"}]} |
|
|
] |
|
|
|
|
|
inputs = tokenizer.apply_chat_template( |
|
|
messages, |
|
|
add_generation_prompt=True, |
|
|
tokenize=True, |
|
|
return_tensors="pt" |
|
|
).to(model.device) |
|
|
|
|
|
with torch.inference_mode(): |
|
|
outputs = model.generate( |
|
|
inputs, |
|
|
max_new_tokens=512, |
|
|
temperature=0.7, |
|
|
top_p=0.9 |
|
|
) |
|
|
|
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
print(response) |
|
|
``` |
|
|
|
|
|
|
