|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
datasets: |
|
|
- mlabonne/orpo-dpo-mix-40k |
|
|
base_model: |
|
|
- meta-llama/Llama-3.2-1B |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
# Orpo-Llama-3.2-1B-15k |
|
|
|
|
|
AdamLucek/Orpo-Llama-3.2-1B-15k is an [ORPO](https://arxiv.org/abs/2403.07691) fine tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on a subset of 15,000 shuffled entries of [mlabonne/orpo-dpo-mix-40k](https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k). |
|
|
|
|
|
Trained for 7 hours on an L4 GPU with [this training script](https://colab.research.google.com/drive/1KV9AFAfhQCSjF8Ej4rI2ejDmx5AUnqHq?usp=sharing), modified from [Maxime Labonne's original guide](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) |
|
|
|
|
|
For full model details, refer to the base model page [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) |
|
|
|
|
|
## Evaluations |
|
|
|
|
|
In comparsion to [AdamLucek/Orpo-Llama-3.2-1B-40k](https://huggingface.co/AdamLucek/Orpo-Llama-3.2-1B-40k) using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). |
|
|
|
|
|
| Benchmark | 15k Accuracy | 15k Normalized | 40k Accuracy | 40k Normalized | Notes | |
|
|
|----------------|--------------|----------------|--------------|----------------|-------------------------------------------| |
|
|
| AGIEval | 22.14% | 21.01% | 23.57% | 23.26% | 0-Shot Average across multiple reasoning tasks | |
|
|
| GPT4ALL | 51.15% | 54.38% | 51.63% | 55.00% | 0-Shot Average across all categories | |
|
|
| TruthfulQA | 42.79% | N/A | 42.14% | N/A | MC2 accuracy | |
|
|
| MMLU | 31.22% | N/A | 31.01% | N/A | 5-Shot Average across all categories | |
|
|
| Winogrande | 61.72% | N/A | 61.12% | N/A | 0-shot evaluation | |
|
|
| ARC Challenge | 32.94% | 36.01% | 33.36% | 37.63% | 0-shot evaluation | |
|
|
| ARC Easy | 64.52% | 60.40% | 65.91% | 60.90% | 0-shot evaluation | |
|
|
| BoolQ | 50.24% | N/A | 52.29% | N/A | 0-shot evaluation | |
|
|
| PIQA | 75.46% | 74.37% | 75.63% | 75.19% | 0-shot evaluation | |
|
|
| HellaSwag | 48.56% | 64.71% | 48.46% | 64.50% | 0-shot evaluation | |
|
|
|
|
|
## Using this Model |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer |
|
|
import transformers |
|
|
import torch |
|
|
|
|
|
# Load Model and Pipeline |
|
|
model = "AdamLucek/Orpo-Llama-3.2-1B-15k" |
|
|
|
|
|
pipeline = transformers.pipeline( |
|
|
"text-generation", |
|
|
model=model, |
|
|
torch_dtype=torch.float16, |
|
|
device_map="auto", |
|
|
) |
|
|
|
|
|
# Load Tokenizer |
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
|
|
|
|
# Generate Message |
|
|
messages = [{"role": "user", "content": "What is a language model?"}] |
|
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
|
print(outputs[0]["generated_text"]) |
|
|
``` |
|
|
|
|
|
## Training Statistics |
|
|
|
|
|
<div style="display: grid; grid-template-columns: repeat(2, 1fr); gap: 5px; max-width: 1000px;"> |
|
|
<div> |
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/p_GHj_vst0xnC7tBznwRk.png" alt="Panel 1" style="width: 100%; height: auto;"> |
|
|
</div> |
|
|
<div> |
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/AT6XO0WuHOWICT5omJ1L5.png" alt="Panel 2" style="width: 100%; height: auto;"> |
|
|
</div> |
|
|
<div> |
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/XOXtthQ1RWxzcIP6V8-o_.png" alt="Panel 3" style="width: 100%; height: auto;"> |
|
|
</div> |
|
|
<div> |
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/WmV9BWOBxElAvZ3aClgUu.png" alt="Panel 4" style="width: 100%; height: auto;"> |
|
|
</div> |
|
|
</div> |
