README.md

---
library_name: peft
base_model: tiiuae/falcon-7b
---

### Direct Use

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "Dhruvil47/falcon-7b-bioarxiv-ckpt-3.5"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
)
sequences = pipeline(
   "NKX2-1 works through",
    max_length=200,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

```