README.md

---
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: TinyAITA
  results: []
---

<!-- 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. -->

# TinyAITA

This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.

## Model description

```py
import torch
from transformers import pipeline, AutoTokenizer, TextStreamer
import re
tokenizer = AutoTokenizer.from_pretrained("TheBossLevel123/TinyAITA")
pipe = pipeline("text-generation", model="TheBossLevel123/TinyAITA", torch_dtype=torch.bfloat16, device_map="auto")

streamer=TextStreamer(tokenizer)
```
```py
prompt = 'AITA for XYZ?'
outputs = pipe(prompt, max_new_tokens=1024, do_sample=True, temperature=0.9, streamer=streamer, eos_token_id=tokenizer.encode("<|im_end|>"))
if outputs and "generated_text" in outputs[0]:
    text = outputs[0]["generated_text"]
    print(f"Prompt: {prompt}")
    print("")
    print(text)
```

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 200
- mixed_precision_training: Native AMP

### Training results



### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1