Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Llama-3.1-Nemotron-lorablated-70B - GGUF - Model creator: https://huggingface.co/nbeerbower/ - Original model: https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Llama-3.1-Nemotron-lorablated-70B.Q2_K.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.Q2_K.gguf) | Q2_K | 24.56GB | | [Llama-3.1-Nemotron-lorablated-70B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.IQ3_XS.gguf) | IQ3_XS | 27.29GB | | [Llama-3.1-Nemotron-lorablated-70B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.IQ3_S.gguf) | IQ3_S | 28.79GB | | [Llama-3.1-Nemotron-lorablated-70B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.Q3_K_S.gguf) | Q3_K_S | 28.79GB | | [Llama-3.1-Nemotron-lorablated-70B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.IQ3_M.gguf) | IQ3_M | 29.74GB | | [Llama-3.1-Nemotron-lorablated-70B.Q3_K.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.Q3_K.gguf) | Q3_K | 31.91GB | | [Llama-3.1-Nemotron-lorablated-70B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.Q3_K_M.gguf) | Q3_K_M | 31.91GB | | [Llama-3.1-Nemotron-lorablated-70B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.Q3_K_L.gguf) | Q3_K_L | 34.59GB | | [Llama-3.1-Nemotron-lorablated-70B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.IQ4_XS.gguf) | IQ4_XS | 35.64GB | | [Llama-3.1-Nemotron-lorablated-70B.Q4_0.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/blob/main/Llama-3.1-Nemotron-lorablated-70B.Q4_0.gguf) | Q4_0 | 37.22GB | | [Llama-3.1-Nemotron-lorablated-70B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | IQ4_NL | 37.58GB | | [Llama-3.1-Nemotron-lorablated-70B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q4_K_S | 37.58GB | | [Llama-3.1-Nemotron-lorablated-70B.Q4_K.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q4_K | 39.6GB | | [Llama-3.1-Nemotron-lorablated-70B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q4_K_M | 39.6GB | | [Llama-3.1-Nemotron-lorablated-70B.Q4_1.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q4_1 | 41.27GB | | [Llama-3.1-Nemotron-lorablated-70B.Q5_0.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q5_0 | 45.32GB | | [Llama-3.1-Nemotron-lorablated-70B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q5_K_S | 45.32GB | | [Llama-3.1-Nemotron-lorablated-70B.Q5_K.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q5_K | 46.52GB | | [Llama-3.1-Nemotron-lorablated-70B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q5_K_M | 46.52GB | | [Llama-3.1-Nemotron-lorablated-70B.Q5_1.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q5_1 | 49.36GB | | [Llama-3.1-Nemotron-lorablated-70B.Q6_K.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q6_K | 53.91GB | | [Llama-3.1-Nemotron-lorablated-70B.Q8_0.gguf](https://huggingface.co/RichardErkhov/nbeerbower_-_Llama-3.1-Nemotron-lorablated-70B-gguf/tree/main/) | Q8_0 | 69.83GB | Original model description: --- license: llama3.1 library_name: transformers tags: - mergekit - merge base_model: - nvidia/Llama-3.1-Nemotron-70B-Instruct-HF - mlabonne/Llama-3-70B-Instruct-abliterated-LORA model-index: - name: Llama-3.1-Nemotron-lorablated-70B results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 71.47 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 48.06 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 23.34 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 0.89 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 14.92 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 43.46 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B name: Open LLM Leaderboard --- ![image/png](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B/resolve/main/nemotron.png?download=true) # Llama-3.1-Nemotron-lorablated-70B An uncensored version of [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) created by merging [mlabonne/Llama-3-70B-Instruct-abliterated-LORA](https://huggingface.co/mlabonne/Llama-3-70B-Instruct-abliterated-LORA) using [task arithmetic](https://arxiv.org/abs/2212.04089). ## Method This model was created using [mergekit](https://github.com/cg123/mergekit). From Ubuntu 24.04 (as root): ``` apt update apt install pipx git clone https://github.com/arcee-ai/mergekit.git cd mergekit && pipx install -e . mergekit-yaml config.yaml Llama-3.1-Nemotron-lorablated-70B --allow-crimes --lora-merge-cache=./cache ``` See [@mlabonne](https://huggingface.co/mlabonne)'s [Llama-3.1-70B-Instruct-lorablated](https://huggingface.co/mlabonne/Llama-3.1-70B-Instruct-lorablated) for more details on how the LoRA was extracted. ### Configuration The following YAML configuration was used to produce this model: ```yaml base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF+mlabonne/Llama-3-70B-Instruct-abliterated-LORA dtype: bfloat16 merge_method: task_arithmetic parameters: normalize: false slices: - sources: - layer_range: [0, 80] model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF+mlabonne/Llama-3-70B-Instruct-abliterated-LORA parameters: weight: 1.0 ``` ### Acknowlegements Thanks to [@mlabonne](https://huggingface.co/mlabonne), [@grimjim](https://huggingface.co/grimjim), and [@failspy](https://huggingface.co/failspy) for pioneering this technique for uncensoring models. Compute provided by [Hetzner](https://www.hetzner.com/) and funded by [Schneewolf Labs](https://schneewolflabs.com/). # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbeerbower__Llama-3.1-Nemotron-lorablated-70B) | Metric |Value| |-------------------|----:| |Avg. |33.69| |IFEval (0-Shot) |71.47| |BBH (3-Shot) |48.06| |MATH Lvl 5 (4-Shot)|23.34| |GPQA (0-shot) | 0.89| |MuSR (0-shot) |14.92| |MMLU-PRO (5-shot) |43.46|