--- library_name: transformers tags: - mergekit - merge base_model: - NousResearch/Hermes-3-Llama-3.1-70B - mlabonne/Llama-3-70B-Instruct-abliterated-LORA model-index: - name: Hermes-3-Llama-3.1-70B-lorablated 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: 71.44 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated 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: 52.34 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated 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: 13.82 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated 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: 13.2 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated 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: 22.02 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated 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: 41.37 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Hermes-3-Llama-3.1-70B-lorablated name: Open LLM Leaderboard --- # 🪽 Hermes-3-Llama-3.1-70B-lorablated ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/4Hbw5n68jKUSBQeTqQIeT.png)
8B version: mlabonne/Hermes-3-Llama-3.1-8B-lorablated
This is an uncensored version of [NousResearch/Hermes-3-Llama-3.1-70B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B) using lorablation. You can see in the following example how Hermes 3 refuses to answer a legitimate question while the abliterated model complies: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2-ZRBvlZxvIr_Ag_ynNkk.png) The recipe is based on @grimjim's [grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter](https://huggingface.co/grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter) (special thanks): 1. **Extraction**: We extract a LoRA adapter by comparing two models: a censored Llama 3 ([meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)) and an abliterated Llama 3.1 ([failspy/Meta-Llama-3.1-70B-Instruct-abliterated](https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated)). 2. **Merge**: We merge this new LoRA adapter using [task arithmetic](https://arxiv.org/abs/2212.04089) to the censored [NousResearch/Hermes-3-Llama-3.1-70B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B) to abliterate it. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/JdYyK-HLHbyBiHvg-Nvsn.png) See [this article](https://huggingface.co/blog/mlabonne/abliteration) to learn more about abliteration. ## ⚡ Quantization * **GGUF**: https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-70B-lorablated-GGUF ## 🧩 Configuration This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Hermes-3-Llama-3.1-70B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B) + Llama-3.1-70B-Instruct-abliterated-LORA as a base. The following YAML configuration was used to produce this model: ```yaml base_model: NousResearch/Hermes-3-Llama-3.1-70B+mlabonne/Llama-3.1-70B-Instruct-abliterated-LORA dtype: bfloat16 merge_method: task_arithmetic parameters: normalize: false slices: - sources: - layer_range: [0, 32] model: NousResearch/Hermes-3-Llama-3.1-70B+mlabonne/Llama-3.1-70B-Instruct-abliterated-LORA parameters: weight: 1.0 ``` You can reproduce this model using the following commands: ```bash # Setup git clone https://github.com/arcee-ai/mergekit.git cd mergekit && pip install -e . pip install bitsandbytes # Merge using previous config mergekit-yaml config.yaml Hermes-3-Llama-3.1-70B-lorablated --allow-crimes --lora-merge-cache=./cache ``` # [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_mlabonne__Hermes-3-Llama-3.1-70B-lorablated) | Metric |Value| |-------------------|----:| |Avg. |35.70| |IFEval (0-Shot) |71.44| |BBH (3-Shot) |52.34| |MATH Lvl 5 (4-Shot)|13.82| |GPQA (0-shot) |13.20| |MuSR (0-shot) |22.02| |MMLU-PRO (5-shot) |41.37|