Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-6_5bpw_exl2

Exllamav2 quant (exl2 / 6.5 bpw) made with ExLlamaV2 v0.1.1

Other EXL2 quants:

Quant	Model Size	lm_head
2.2	3250 MB	6
2.5	3479 MB	6
3.0	3895 MB	6
3.5	4311 MB	6
3.75	4519 MB	6
4.0	4727 MB	6
4.25	4933 MB	6
5.0	5558 MB	6
6.0	6490 MB	8
6.5	6881 MB	8
8.0	8073 MB	8

Llama-3-8B-Instruct-abliterated-dpomix

This model is an experimental DPO fine-tune of an abliterated Llama 3 8B Instruct model on the full mlabonne/orpo-dpo-mix-40k dataset. It improves Llama 3 8B Instruct's performance while being uncensored.

🏆 Evaluation

Nous

Model	Average	AGIEval	GPT4All	TruthfulQA	Bigbench
mlabonne/Llama-3-8B-Instruct-abliterated-dpomix 📄	52.26	41.6	69.95	54.22	43.26
meta-llama/Meta-Llama-3-8B-Instruct 📄	51.34	41.22	69.86	51.65	42.64
failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 📄	51.21	40.23	69.5	52.44	42.69
abacusai/Llama-3-Smaug-8B 📄	49.65	37.15	69.12	51.66	40.67
mlabonne/OrpoLlama-3-8B 📄	48.63	34.17	70.59	52.39	37.36
meta-llama/Meta-Llama-3-8B 📄	45.42	31.1	69.95	43.91	36.7

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Llama-3-8B-Instruct-abliterated-dpomix"
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"])