README.md

metadata

language:
  - tr
  - en
  - es
license: apache-2.0
library_name: transformers
tags:
  - Generative AI
  - text-generation-inference
  - text-generation
  - peft
  - unsloth

Model Trained By Meforgers

This model was trained by Meforgers for the futuristic projects.

• Firstly

  -If u want to use unsloth; For Pytorch 2.3.0: Use the "ampere" path for newer RTX 30xx GPUs or higher.

      pip install "unsloth[cu118-torch230] @ git+https://github.com/unslothai/unsloth.git"
      pip install "unsloth[cu121-torch230] @ git+https://github.com/unslothai/unsloth.git"
      pip install "unsloth[cu118-ampere-torch230] @ git+https://github.com/unslothai/unsloth.git"
      pip install "unsloth[cu121-ampere-torch230] @ git+https://github.com/unslothai/unsloth.git"
  

  -Also you can use another system

• Usage

  from unsloth import FastLanguageModel
  import torch
  
  # Variable side
  max_seq_length = 512 
  dtype = torch.float16 
  load_in_4bit = True
  
  # Alpaca prompt
  alpaca_prompt = """### Instruction:
  {0}
  
  ### Input:
  {1}
  
  ### Response:
  {2}
  """
  
  model, tokenizer = FastLanguageModel.from_pretrained(
      model_name="Meforgers/Aixr",
      max_seq_length=max_seq_length,
      dtype=dtype,
      load_in_4bit=load_in_4bit,
  )
  
  FastLanguageModel.for_inference(model)
  
  inputs = tokenizer(
      [
          alpaca_prompt.format(
              "Can u text me basic python code?",  # instruction side (You need to change that side)
              "",  # input
              "",  # output - leave this blank for generation!
          )
      ],
      return_tensors="pt"
  ).to("cuda")
  
  outputs = model.generate(**inputs, max_new_tokens=128, use_cache=True)
  print(tokenizer.batch_decode(outputs))