README.md

---
license: apache-2.0
datasets:
- medalpaca/medical_meadow_wikidoc_patient_information
pipeline_tag: text-generation
---
# llama-2-7b-chat-MEDS-12

This is a `llama-2-7b-chat-hf` model fine-tuned using QLoRA (4-bit precision) on the [`s200862/medical_qa_meds`](https://huggingface.co/datasets/s200862/medical_qa_meds) dataset. This is an adapted version of the [`medalpaca/medical_meadow_wikidoc_patient_information`](https://huggingface.co/datasets/medalpaca/medical_meadow_wikidoc_patient_information) dataset to match llama-2's instruction format.

## 🔧 Training

It was trained on-premise in a jupyter notebook using an Nvidia RTX A4000 GPU with 16GB of VRAM and 16 GB of system RAM.

## 💻 Usage

It is intended to give answers to medical questions.

``` python
# pip install transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "s200862/llama-2-7b-chat-MEDS-12"
prompt = "What causes Allergy?"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

sequences = pipeline(
    f'<s>[INST] {prompt} [/INST]',
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=200,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")
```