---
library_name: peft
---
## Training procedure


The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions

- PEFT 0.4.0

### How to Get Started with the Model

```python
from transformers import pipeline
from transformers import AutoTokenizer
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM , BitsAndBytesConfig
import torch
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=getattr(torch, "float16"),
    bnb_4bit_use_double_quant=False)
model = AutoModelForCausalLM.from_pretrained(
        "meta-llama/Llama-2-13b-hf",
        quantization_config=bnb_config,
        device_map={"": 0})
model.config.use_cache = False
model.config.pretraining_tp = 1
model = PeftModel.from_pretrained(model, "TuningAI/Llama2_13B_startup_Assistant")

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-13b-hf", trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"
while 1:
  input_text = input(">>>")
  prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n {input_text}. [/INST]"
  num_new_tokens = 60
  num_prompt_tokens = len(tokenizer(prompt)['input_ids'])
  max_length = num_prompt_tokens + num_new_tokens
  pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=max_length)
  result = pipe(prompt)
  print(result[0]['generated_text'].replace(prompt, ''))
```