Downloads · 30 days
69
8% of all-time downloads
RichardErkhov/mlabonne_-_OrpoLlama-3-8B-gguf
mlabonne_-_OrpoLlama-3-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
69
8% of all-time downloads
All-time downloads
904
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
OrpoLlama-3-8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| OrpoLlama-3-8B.Q2_K.gguf | Q2_K | 2.96GB |
| OrpoLlama-3-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| OrpoLlama-3-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| OrpoLlama-3-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| OrpoLlama-3-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| OrpoLlama-3-8B.Q3_K.gguf | Q3_K | 3.74GB |
| OrpoLlama-3-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| OrpoLlama-3-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| OrpoLlama-3-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| OrpoLlama-3-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| OrpoLlama-3-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| OrpoLlama-3-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| OrpoLlama-3-8B.Q4_K.gguf | Q4_K | 4.58GB |
| OrpoLlama-3-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| OrpoLlama-3-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| OrpoLlama-3-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| OrpoLlama-3-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| OrpoLlama-3-8B.Q5_K.gguf | Q5_K | 5.34GB |
| OrpoLlama-3-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| OrpoLlama-3-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| OrpoLlama-3-8B.Q6_K.gguf | Q6_K | 6.14GB |
| OrpoLlama-3-8B.Q8_0.gguf | Q8_0 | 7.95GB |
language:

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
This model uses a context window of 8k. It was trained with the ChatML template.
Thanks to bartowski, solidrust, and LoneStriker for the quantized models.
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.

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

!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"])