---
base_model: unsloth/llama-2-7b-bnb-4bit
library_name: peft
license: apache-2.0
datasets: hermeschen1116/daily_dialog_for_RG
tags:
- trl
- unsloth
model-index:
- name: response_generator_for_emotion_chat_bot
  results: []
language:
- en
pipeline_tag: text-generation
metrics: 
- accuracy
- f1-score
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Response Generator for [Emotion Chat Bot](https://github.com/hermeschen1116/chat-bot)

This model is a fine-tuned version of [unsloth/llama-2-7b-bnb-4bit](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) on [hermeschen1116/daily_dialog_for_RG](https://huggingface.co/datasets/hermeschen1116/daily_dialog_for_RG), self modified version of [daily_dialog](li2017dailydialog/daily_dialog).

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- system_prompt: ""
- learning_rate: 0.0002
- weight_decay: 0.001
- max_grad_norm: 0.3
- warmup_ratio: 0.03
- max_steps: -1
- train_batch_size: 4
- seed: 42
- optimizer: paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
- init_lora_weights: true
- lora_rank: 16
- lora_alpha: 16
- lora_dropout: 0.1
- use_rslora: true

### Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Trl 0.8.6
- Bitsandbytes