--- license: other datasets: - mlabonne/orpo-dpo-mix-40k tags: - abliterated --- **Exllamav2** quant (**exl2** / **3.5 bpw**) made with ExLlamaV2 v0.1.1 Other EXL2 quants: | **Quant** | **Model Size** | **lm_head** | | ----- | ---------- | ------- | |
**[2.2](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-2_2bpw_exl2)**
|
3250 MB
|
6
| |
**[2.5](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-2_5bpw_exl2)**
|
3479 MB
|
6
| |
**[3.0](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-3_0bpw_exl2)**
|
3895 MB
|
6
| |
**[3.5](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-3_5bpw_exl2)**
|
4311 MB
|
6
| |
**[3.75](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-3_75bpw_exl2)**
|
4519 MB
|
6
| |
**[4.0](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-4_0bpw_exl2)**
|
4727 MB
|
6
| |
**[4.25](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-4_25bpw_exl2)**
|
4933 MB
|
6
| |
**[5.0](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-5_0bpw_exl2)**
|
5558 MB
|
6
| |
**[6.0](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-6_0bpw_exl2)**
|
6490 MB
|
8
| |
**[6.5](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-6_5bpw_exl2)**
|
6881 MB
|
8
| |
**[8.0](https://huggingface.co/Zoyd/mlabonne_Llama-3-8B-Instruct-abliterated-dpomix-8_0bpw_exl2)**
|
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](https://huggingface.co/datasets/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**](https://huggingface.co/mlabonne/Llama-3-8B-Instruct-abliterated-dpomix) [📄](https://gist.github.com/mlabonne/d711548df70e2c04771cc68ab33fe2b9) | **52.26** | **41.6** | **69.95** | **54.22** | **43.26** | | [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) [📄](https://gist.github.com/mlabonne/8329284d86035e6019edb11eb0933628) | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 | | [failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3) [📄](https://gist.github.com/mlabonne/f46cce0262443365e4cce2b6fa7507fc) | 51.21 | 40.23 | 69.5 | 52.44 | 42.69 | | [abacusai/Llama-3-Smaug-8B](https://huggingface.co/abacusai/Llama-3-Smaug-8B) [📄](https://gist.github.com/mlabonne/91369d9c372f80b6a42a978b454d3b5e) | 49.65 | 37.15 | 69.12 | 51.66 | 40.67 | | [mlabonne/OrpoLlama-3-8B](https://huggingface.co/mlabonne/OrpoLlama-3-8B) [📄](https://gist.github.com/mlabonne/22896a1ae164859931cc8f4858c97f6f) | 48.63 | 34.17 | 70.59 | 52.39 | 37.36 | | [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) [📄](https://gist.github.com/mlabonne/616b6245137a9cfc4ea80e4c6e55d847) | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 | ## 💻 Usage ```python !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"]) ```