YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co./docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Heart_Stolen-8B-Model_Stock - GGUF
- Model creator: https://huggingface.co./DreadPoor/
- Original model: https://huggingface.co./DreadPoor/Heart_Stolen-8B-Model_Stock/
Original model description:
license: apache-2.0 library_name: transformers tags: - mergekit - merge base_model: - akjindal53244/Llama-3.1-Storm-8B - ResplendentAI/NoWarning_Llama3 - Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 - kloodia/lora-8b-physic - Sao10K/L3-8B-Stheno-v3.2 - ResplendentAI/Smarts_Llama3 - NeverSleep/Lumimaid-v0.2-8B - ResplendentAI/Theory_of_Mind_Llama3 - DreadPoor/ScaduTorrent1.1-8b-model_stock - kloodia/lora-8b-medic - mlabonne/Hermes-3-Llama-3.1-8B-lorablated - kloodia/lora-8b-bio model-index: - name: Heart_Stolen-8B-Model_Stock 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: 72.45 name: strict accuracy source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock 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: 34.44 name: normalized accuracy source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock 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: 14.65 name: exact match source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock 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: 8.95 name: acc_norm source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock 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: 12.36 name: acc_norm source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock 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: 31.04 name: accuracy source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Heart_Stolen-8B-Model_Stock name: Open LLM Leaderboard
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using Sao10K/L3-8B-Stheno-v3.2 + ResplendentAI/Smarts_Llama3 as a base.
Models Merged
The following models were included in the merge:
- akjindal53244/Llama-3.1-Storm-8B + ResplendentAI/NoWarning_Llama3
- Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 + kloodia/lora-8b-physic
- NeverSleep/Lumimaid-v0.2-8B + ResplendentAI/Theory_of_Mind_Llama3
- DreadPoor/ScaduTorrent1.1-8b-model_stock + kloodia/lora-8b-medic
- mlabonne/Hermes-3-Llama-3.1-8B-lorablated + kloodia/lora-8b-bio
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2+kloodia/lora-8b-physic
- model: akjindal53244/Llama-3.1-Storm-8B+ResplendentAI/NoWarning_Llama3
- model: DreadPoor/ScaduTorrent1.1-8b-model_stock+kloodia/lora-8b-medic
- model: NeverSleep/Lumimaid-v0.2-8B+ResplendentAI/Theory_of_Mind_Llama3
- model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated+kloodia/lora-8b-bio
merge_method: model_stock
base_model: Sao10K/L3-8B-Stheno-v3.2+ResplendentAI/Smarts_Llama3
normalize: false
int8_mask: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 28.98 |
IFEval (0-Shot) | 72.45 |
BBH (3-Shot) | 34.44 |
MATH Lvl 5 (4-Shot) | 14.65 |
GPQA (0-shot) | 8.95 |
MuSR (0-shot) | 12.36 |
MMLU-PRO (5-shot) | 31.04 |
- Downloads last month
- 0