File size: 1,052 Bytes
fbc68f7 8570f4f fbc68f7 81cb633 fbc68f7 81cb633 8570f4f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 |
---
license: mit
language:
- bn
pipeline_tag: question-answering
---
```bash
from transformers import TextStreamer
from unsloth import FastLanguageModel
import torch
alpaca_prompt = """
### Instruction:
{}
### Input:
{}
### Response:
{}"""
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "Bikas0/Bengali-Question-Answer-Llama3", # YOUR MODEL YOU USED FOR TRAINING
max_seq_length = 2048,
dtype = torch.float16,
load_in_4bit = True,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
inputs = tokenizer(
[
alpaca_prompt.format(
"Please provide a detailed answer to the following question", # instruction
"বাংলা একাডেমি আইন কোন কারণে সদস্যপদ বাতিল করা হবে ?", # input
"", # output - leave this blank for generation!
)
], return_tensors = "pt").to("cuda")
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 2048)
``` |