README.md

metadata

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

Model Trained By Meforgers

This model, named 'Aixr,' is designed for science and artificial intelligence development. You can use it as the foundation for many of your scientific projects and interesting ideas. In short, Aixr is an artificial intelligence model that is based on futurism and innovation.

• Firstly

  -If you intend to use unsloth with Pytorch 1.3.0: Utilize 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))