đ Llama-3-8b base model trained on Orca Style Mini Datasets
This is a Llama-3-8b base model trained on Orca Style Mini Datasets, which can be used for text2text generation tasks.
đ Quick Start
This model is a Llama-3-8b base model trained on Orca Style Mini Datasets. It can be used for text2text generation tasks. You can use the following code to load and use the model.
⨠Features
- Customizable: By providing proper credit and attribution, you can use this model as a foundational base for further DPO/PPO tuning or Merges.
- Evaluated: Evaluated on a wide range of tasks using Language Model Evaluation Harness from EleutherAI.
đĻ Installation
This model can be installed using the transformers
library. You can use the following command to install the library:
pip install transformers
đģ Usage Examples
Basic Usage
Here is the ChatML prompt format:
<|im_start|>system
You are Orca Mini, a helpful AI assistant.<|im_end|>
<|im_start|>user
Hello Orca Mini, what can you do for me?<|im_end|>
<|im_start|>assistant
Below shows a code example on how to use this model:
from transformers import AutoModel, AutoTokenizer
model_slug = "pankajmathur/orca_mini_v4_8b"
model = AutoModel.from_pretrained(model_slug)
tokenizer = AutoTokenizer.from_pretrained(model_slug)
messages = [
{"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},
{"role": "user", "content": "Hello Orca Mini, what can you do for me?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
đ Documentation
NOTICE
By providing proper credit and attribution, you are granted permission to use this model as a foundational base for further DPO/PPO tuning or Merges.
I actively encourage users to customize and enhance the model according to their specific needs, as this version is designed to be a comprehensive, fully fine-tuned general model.
Dive in and innovate!
Evaluation
We evaluated this model on a wide range of tasks using Language Model Evaluation Harness from EleutherAI.
Here are the results on similar metrics used by HuggingFaceH4 Open LLM Leaderboard
Property |
Details |
Avg. |
66.65 |
AI2 Reasoning Challenge (25-Shot) |
58.02 |
HellaSwag (10-Shot) |
81.65 |
MMLU (5-Shot) |
63.23 |
TruthfulQA (0-shot) |
55.78 |
Winogrande (5-shot) |
73.95 |
GSM8k (5-shot) |
67.25 |
Quants
- GGUF : Coming Soon
- AWQ: Coming Soon
đ License
This model is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT
"Obsessed with GenAI's potential? So am I ! Let's create together đ https://www.linkedin.com/in/pankajam"