Llama-3.1-8B-Instruct-abliterated_via_adapter/README.md

license, library_name, tags, base_model, pipeline_tag, model-index

license	library_name	tags	base_model	pipeline_tag	model-index
llama3.1	transformers	mergekit merge	meta-llama/Meta-Llama-3.1-8B-Instruct grimjim/Llama-3-Instruct-abliteration-LoRA-8B	text-generation	name results Llama-3.1-8B-Instruct-abliterated_via_adapter 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 48.7 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter 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 29.42 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter 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 12.39 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter 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 8.5 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter 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 9.26 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter 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 29.46 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter Open LLM Leaderboard

Llama-3.1-8B-Instruct-abliterated_via_adapter

This model is a merge of pre-trained language models created using mergekit.

A LoRA was applied to "abliterate" refusals in meta-llama/Meta-Llama-3.1-8B-Instruct. The result appears to work despite the LoRA having been derived from Llama 3 instead of Llama 3.1, which implies that there is significant feature commonality between the 3 and 3.1 models.

The LoRA was extracted from failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 using meta-llama/Meta-Llama-3-8B-Instruct as a base.

Built with Llama.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using meta-llama/Meta-Llama-3.1-8B-Instruct + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 32]
    model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    parameters:
      weight: 1.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	22.95
IFEval (0-Shot)	48.70
BBH (3-Shot)	29.42
MATH Lvl 5 (4-Shot)	12.39
GPQA (0-shot)	8.50
MuSR (0-shot)	9.26
MMLU-PRO (5-shot)	29.46