---
library_name: peft
---

## Model Usage

```python
import wandb
import os
import torch

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TrainingArguments
from peft import LoraConfig, prepare_model_for_kbit_training, get_peft_model, AutoPeftModelForCausalLM
from datasets import load_dataset
from random import randrange
from trl import SFTTrainer
from huggingface_hub import login


tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen25-7b-mono", trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token

device_map = {"":0}
model = AutoPeftModelForCausalLM.from_pretrained("0xk1h0/codegen2.5-7b-py150k-r20-QLoRA", device_map=device_map, torch_dtype=torch.bfloat16)
text ="""
# Generate AES MODE encrypt python function.
"""
inputs = tokenizer(text, return_tensors="pt").to("cuda")
outputs = model.generate(
    input_ids=inputs["input_ids"].to("cuda"),
    attention_mask=inputs["attention_mask"],
    # max_new_tokens=50,
    max_length=256,
    do_sample=True,
    temperature = 0.4,
    top_p=0.95,
    pad_token_id=tokenizer.eos_token_id
    )

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## 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

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 0.5.0

- PEFT 0.5.0