mlabonne / OrpoLlama-3-8B

huggingface.co
Total runs: 80
24-hour runs: 0
7-day runs: -4
30-day runs: 40
Model's Last Updated: June 15 2024
text-generation

Introduction of OrpoLlama-3-8B

Model Details of OrpoLlama-3-8B

OrpoLlama-3-8B

This is an ORPO fine-tune of meta-llama/Meta-Llama-3-8B on mlabonne/orpo-dpo-mix-40k created for this article .

It's a successful fine-tune that follows the ChatML template!

Try the demo : https://huggingface.co/spaces/mlabonne/OrpoLlama-3-8B

🔎 Application

This model uses a context window of 8k. It was trained with the ChatML template.

⚡ Quantized models

Thanks to bartowski, solidrust, and LoneStriker for the quantized models.

🏆 Evaluation
Nous

OrpoLlama-4-8B outperforms Llama-3-8B-Instruct on the GPT4All and TruthfulQA datasets.

Evaluation performed using LLM AutoEval , see the entire leaderboard here .

Model Average AGIEval GPT4All TruthfulQA Bigbench
meta-llama/Meta-Llama-3-8B-Instruct 📄 51.34 41.22 69.86 51.65 42.64
mlabonne/OrpoLlama-3-8B 📄 48.63 34.17 70.59 52.39 37.36
mlabonne/OrpoLlama-3-8B-1k 📄 46.76 31.56 70.19 48.11 37.17
meta-llama/Meta-Llama-3-8B 📄 45.42 31.1 69.95 43.91 36.7

mlabonne/OrpoLlama-3-8B-1k corresponds to a version of this model trained on 1K samples (you can see the parameters in this article ). The current version was trained on a full epoch.

Open LLM Leaderboard

image/png

📈 Training curves

You can find the experiment on W&B at this address .

image/png

💻 Usage
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/OrpoLlama-3-8B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

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"])

Runs of mlabonne OrpoLlama-3-8B on huggingface.co

80
Total runs
0
24-hour runs
-2
3-day runs
-4
7-day runs
40
30-day runs

More Information About OrpoLlama-3-8B huggingface.co Model

More OrpoLlama-3-8B license Visit here:

https://choosealicense.com/licenses/other

OrpoLlama-3-8B huggingface.co

OrpoLlama-3-8B huggingface.co is an AI model on huggingface.co that provides OrpoLlama-3-8B's model effect (), which can be used instantly with this mlabonne OrpoLlama-3-8B model. huggingface.co supports a free trial of the OrpoLlama-3-8B model, and also provides paid use of the OrpoLlama-3-8B. Support call OrpoLlama-3-8B model through api, including Node.js, Python, http.

OrpoLlama-3-8B huggingface.co Url

https://huggingface.co/mlabonne/OrpoLlama-3-8B

mlabonne OrpoLlama-3-8B online free

OrpoLlama-3-8B huggingface.co is an online trial and call api platform, which integrates OrpoLlama-3-8B's modeling effects, including api services, and provides a free online trial of OrpoLlama-3-8B, you can try OrpoLlama-3-8B online for free by clicking the link below.

mlabonne OrpoLlama-3-8B online free url in huggingface.co:

https://huggingface.co/mlabonne/OrpoLlama-3-8B

OrpoLlama-3-8B install

OrpoLlama-3-8B is an open source model from GitHub that offers a free installation service, and any user can find OrpoLlama-3-8B on GitHub to install. At the same time, huggingface.co provides the effect of OrpoLlama-3-8B install, users can directly use OrpoLlama-3-8B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

OrpoLlama-3-8B install url in huggingface.co:

https://huggingface.co/mlabonne/OrpoLlama-3-8B

Url of OrpoLlama-3-8B

OrpoLlama-3-8B huggingface.co Url

Provider of OrpoLlama-3-8B huggingface.co

mlabonne
ORGANIZATIONS

Other API from mlabonne

huggingface.co

Total runs: 156
Run Growth: -18
Growth Rate: -11.54%
Updated:March 04 2024
huggingface.co

Total runs: 75
Run Growth: 24
Growth Rate: 32.00%
Updated:March 04 2024