import torch
major_version, minor_version = torch.cuda.get_device_capability()
 

!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
if major_version >= 8:
    # Use this for new GPUs like Ampere, Hopper GPUs (RTX 30xx, RTX 40xx, A100, H100, L40)
    !pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes
else:
    # Use this for older GPUs (V100, Tesla T4, RTX 20xx)
    !pip install --no-deps xformers trl peft accelerate bitsandbytes
pass



from unsloth import FastLanguageModel
import torch
max_seq_length = 2048
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = False 
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "Xhaheen/Shaheen_Gemma_Urdu_",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    device_map="auto"
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference

input_prompt = """
### Instruction:
{}

### Input:
{}

### Response:
{}"""

input_text = input_prompt.format(
        "دیئے گئے موضوع کے بارے میں ایک مختصر پیراگراف لکھیں۔", # instruction
        "قابل تجدید توانائی کے استعمال کی اہمیت", # input
        "", # output - leave this blank for generation!
    )

inputs = tokenizer([input_text], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True)

response = tokenizer.batch_decode(outputs)

Inference With Inference with HuggingFace transformers

python3

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

model = AutoPeftModelForCausalLM.from_pretrained(
    "Xhaheen/Shaheen_Gemma_Urdu_",
    load_in_4bit = False
)
tokenizer = AutoTokenizer.from_pretrained("Xhaheen/Shaheen_Gemma_Urdu_")


input_prompt = """
### Instruction:
{}

### Input:
{}

### Response:
{}"""



input_text = input_prompt.format(
        "دیئے گئے موضوع کے بارے میں ایک مختصر پیراگراف لکھیں۔", # instruction
        "قابل تجدید توانائی کے استعمال کی اہمیت", # input
        "", # output - leave this blank for generation!
    )

inputs = tokenizer([input_text], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True)
response = tokenizer.batch_decode(outputs)[0]