mpasila/Llama3-8B-OpenHermes-DPO-exl2-4bpw

This is an ExLlamaV2 quantized model in 4bpw of Muhammad2003/Llama3-8B-OpenHermes-DPO using the default calibration dataset.

Original Model card:

Llama3-8B-OpenHermes-DPO

Llama3-8B-OpenHermes-DPO is DPO-Finetuned model of Llama3-8B, on the OpenHermes-2.5 preference dataset using QLoRA.

• meta-llama/Meta-Llama-3-8B
• mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Muhammad2003/Llama3-8B-OpenHermes-DPO"
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"])

🏆 Evaluation results

Coming Soon