README.md

Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


orpo-lora-phi2 - GGUF
- Model creator: https://huggingface.co/Amu/
- Original model: https://huggingface.co/Amu/orpo-lora-phi2/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [orpo-lora-phi2.Q2_K.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q2_K.gguf) | Q2_K | 1.03GB |
| [orpo-lora-phi2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.IQ3_XS.gguf) | IQ3_XS | 1.12GB |
| [orpo-lora-phi2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.IQ3_S.gguf) | IQ3_S | 1.16GB |
| [orpo-lora-phi2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q3_K_S.gguf) | Q3_K_S | 1.16GB |
| [orpo-lora-phi2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.IQ3_M.gguf) | IQ3_M | 1.23GB |
| [orpo-lora-phi2.Q3_K.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q3_K.gguf) | Q3_K | 1.33GB |
| [orpo-lora-phi2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q3_K_M.gguf) | Q3_K_M | 1.33GB |
| [orpo-lora-phi2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q3_K_L.gguf) | Q3_K_L | 1.47GB |
| [orpo-lora-phi2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.IQ4_XS.gguf) | IQ4_XS | 1.43GB |
| [orpo-lora-phi2.Q4_0.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q4_0.gguf) | Q4_0 | 1.49GB |
| [orpo-lora-phi2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.IQ4_NL.gguf) | IQ4_NL | 1.5GB |
| [orpo-lora-phi2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q4_K_S.gguf) | Q4_K_S | 1.51GB |
| [orpo-lora-phi2.Q4_K.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q4_K.gguf) | Q4_K | 1.62GB |
| [orpo-lora-phi2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q4_K_M.gguf) | Q4_K_M | 1.62GB |
| [orpo-lora-phi2.Q4_1.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q4_1.gguf) | Q4_1 | 1.65GB |
| [orpo-lora-phi2.Q5_0.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q5_0.gguf) | Q5_0 | 1.8GB |
| [orpo-lora-phi2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q5_K_S.gguf) | Q5_K_S | 1.8GB |
| [orpo-lora-phi2.Q5_K.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q5_K.gguf) | Q5_K | 1.87GB |
| [orpo-lora-phi2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q5_K_M.gguf) | Q5_K_M | 1.87GB |
| [orpo-lora-phi2.Q5_1.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q5_1.gguf) | Q5_1 | 1.95GB |
| [orpo-lora-phi2.Q6_K.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q6_K.gguf) | Q6_K | 2.13GB |
| [orpo-lora-phi2.Q8_0.gguf](https://huggingface.co/RichardErkhov/Amu_-_orpo-lora-phi2-gguf/blob/main/orpo-lora-phi2.Q8_0.gguf) | Q8_0 | 2.75GB |




Original model description:
---
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
base_model: microsoft/phi-2
pipeline_tag: text-generation
---

# outputs
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) using [trl](https://github.com/huggingface/trl) on [ultrafeedback dataset](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized).

# What's new
A test for [ORPO: Monolithic Preference Optimization without Reference Model](https://arxiv.org/pdf/2403.07691.pdf) method using trl library.

## How to reproduce
```bash
accelerate launch --config_file=/path/to/trl/examples/accelerate_configs/deepspeed_zero2.yaml \
    --num_processes 8 \
    /path/to/trl/scripts/orpo.py \
    --model_name_or_path="microsoft/phi-2" \
    --per_device_train_batch_size 1 \
    --max_steps 8000 \
    --learning_rate 8e-5 \
    --gradient_accumulation_steps 1 \
    --logging_steps 20 \
    --eval_steps 2000 \
    --output_dir="orpo-lora-phi2" \
    --optim rmsprop \
    --warmup_steps 150 \
    --bf16 \
    --logging_first_step \
    --no_remove_unused_columns \
    --use_peft \
    --lora_r=16 \
    --lora_alpha=16 \
    --dataset HuggingFaceH4/ultrafeedback_binarized
```