Llama-3.1-8B-Lexi-Uncensored-V2-mlx/README.md

license, library_name, base_model, tags, model-index

license	library_name	base_model	tags	model-index
llama3.1	transformers	Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2	mlx	name results Llama-3.1-8B-Lexi-Uncensored-V2 task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 77.92 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 29.69 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 16.92 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 4.36 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 7.77 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 30.9 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 Open LLM Leaderboard

Felprot75/Llama-3.1-8B-Lexi-Uncensored-V2-mlx

The Model Felprot75/Llama-3.1-8B-Lexi-Uncensored-V2-mlx was converted to MLX format from Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Felprot75/Llama-3.1-8B-Lexi-Uncensored-V2-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)