README.md

metadata

language:
  - en
license: apache-2.0
base_model: meta-llama/Llama-2-7b-hf
datasets:
  - screevoai/abbvie
model-index:
  - name: Abbvie-llama2-7b
    results:
      - task:
          name: Causal Language Modeling
          type: causal-language-modeling
        dataset:
          name: Abbvie Dataset
          type: string
          config: None
          split: train, validation, test
          args: None
        metrics:
          - name: Training loss
            type: None
            value: null

Model Details

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the screevoai/abbvie dataset.

Training results

Training Loss	Epoch	Step	Validation Loss
1.4318	7	1100	1.4409

Libraries to Install

• pip install transformers datasets safetensors huggingface-hub accelerator
• pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu

Authentication needed before running the script

Run the following command in the terminal/jupyter_notebook:

• Terminal: huggingface-cli login

• Jupyter_notebook:

  >>> from huggingface_hub import notebook_login
  >>> notebook_login()
  

NOTE: Copy and Paste the token from your Huggingface Account Settings > Access Tokens > Create a new token / Copy the existing one.

Script

>>>from datasets import load_dataset
>>>from transformers import AutoModelForCausalLM, AutoTokenizer

>>> # Load model and Tokenizer
>>> model = AutoModelForCausalLM.from_pretrained("screevoai/abbvie-llama2-7b", device_map = "auto")
>>>  tokenizer = AutoTokenizer.from_pretrained("screevoai/abbvie-llama2-7b")
>>>  tokenizer.padding_side='right'
>>>  tokenizer.pad_token = tokenizer.eos_token

>>> # Load the dataset
>>> ds = load_dataset("screevoai/abbvie", split="test", use_auth_token=True)
>>> sample_prompt = ds["Prompt"][0]  # change the row number for testing different prompts

>>> # Generate answer to the prompt using the model
>>> encoded_input = tokenizer(sample_prompt,  return_tensors="pt", add_special_tokens=True)
>>> model_inputs = encoded_input.to('auto')
>>> generated_ids = model.generate(**model_inputs, max_new_tokens=500, do_sample=True, pad_token_id=tokenizer.eos_token_id)
>>> decoded_output = tokenizer.batch_decode(generated_ids)

>>> print(decoded_output[0].replace(prompt, ""))