Quantization made by Richard Erkhov.

Aspire-8B-model_stock - GGUF

Model creator: https://huggingface.co/DreadPoor/
Original model: https://huggingface.co/DreadPoor/Aspire-8B-model_stock/

Name	Quant method	Size
Aspire-8B-model_stock.Q2_K.gguf	Q2_K	2.96GB
Aspire-8B-model_stock.IQ3_XS.gguf	IQ3_XS	3.28GB
Aspire-8B-model_stock.IQ3_S.gguf	IQ3_S	3.43GB
Aspire-8B-model_stock.Q3_K_S.gguf	Q3_K_S	3.41GB
Aspire-8B-model_stock.IQ3_M.gguf	IQ3_M	3.52GB
Aspire-8B-model_stock.Q3_K.gguf	Q3_K	3.74GB
Aspire-8B-model_stock.Q3_K_M.gguf	Q3_K_M	3.74GB
Aspire-8B-model_stock.Q3_K_L.gguf	Q3_K_L	4.03GB
Aspire-8B-model_stock.IQ4_XS.gguf	IQ4_XS	4.18GB
Aspire-8B-model_stock.Q4_0.gguf	Q4_0	4.34GB
Aspire-8B-model_stock.IQ4_NL.gguf	IQ4_NL	4.38GB
Aspire-8B-model_stock.Q4_K_S.gguf	Q4_K_S	4.37GB
Aspire-8B-model_stock.Q4_K.gguf	Q4_K	4.58GB
Aspire-8B-model_stock.Q4_K_M.gguf	Q4_K_M	4.58GB
Aspire-8B-model_stock.Q4_1.gguf	Q4_1	4.78GB
Aspire-8B-model_stock.Q5_0.gguf	Q5_0	5.21GB
Aspire-8B-model_stock.Q5_K_S.gguf	Q5_K_S	5.21GB
Aspire-8B-model_stock.Q5_K.gguf	Q5_K	5.34GB
Aspire-8B-model_stock.Q5_K_M.gguf	Q5_K_M	3.97GB
Aspire-8B-model_stock.Q5_1.gguf	Q5_1	5.65GB
Aspire-8B-model_stock.Q6_K.gguf	Q6_K	6.14GB
Aspire-8B-model_stock.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: apache-2.0 library_name: transformers tags: - mergekit - merge base_model: - Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 - kloodia/lora-8b-bio - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 - Blackroot/Llama-3-8B-Abomination-LORA - Sao10K/L3-8B-Stheno-v3.2 - grimjim/Llama-3-Instruct-abliteration-LoRA-8B - arcee-ai/Llama-3.1-SuperNova-Lite - grimjim/Llama-3-Instruct-abliteration-LoRA-8B - mlabonne/Hermes-3-Llama-3.1-8B-lorablated - kloodia/lora-8b-physic - aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored - kloodia/lora-8b-medic model-index: - name: Aspire-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: 71.41 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 32.53 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 12.99 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 8.61 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 13.46 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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: 30.7 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-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 + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2+kloodia/lora-8b-bio
  - model: arcee-ai/Llama-3.1-SuperNova-Lite+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
  - model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated+kloodia/lora-8b-physic
  - model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored+kloodia/lora-8b-medic
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1+Blackroot/Llama-3-8B-Abomination-LORA
merge_method: model_stock
base_model: Sao10K/L3-8B-Stheno-v3.2+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
normalize: false
int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.28
IFEval (0-Shot)	71.41
BBH (3-Shot)	32.53
MATH Lvl 5 (4-Shot)	12.99
GPQA (0-shot)	8.61
MuSR (0-shot)	13.46
MMLU-PRO (5-shot)	30.70