Quantization made by Richard Erkhov.

Llama-3-Yggdrasil-2.0-8B - GGUF

Model creator: https://huggingface.co/Locutusque/
Original model: https://huggingface.co/Locutusque/Llama-3-Yggdrasil-2.0-8B/

Name	Quant method	Size
Llama-3-Yggdrasil-2.0-8B.Q2_K.gguf	Q2_K	2.96GB
Llama-3-Yggdrasil-2.0-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3-Yggdrasil-2.0-8B.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3-Yggdrasil-2.0-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3-Yggdrasil-2.0-8B.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3-Yggdrasil-2.0-8B.Q3_K.gguf	Q3_K	3.74GB
Llama-3-Yggdrasil-2.0-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3-Yggdrasil-2.0-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3-Yggdrasil-2.0-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3-Yggdrasil-2.0-8B.Q4_0.gguf	Q4_0	4.34GB
Llama-3-Yggdrasil-2.0-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3-Yggdrasil-2.0-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3-Yggdrasil-2.0-8B.Q4_K.gguf	Q4_K	4.58GB
Llama-3-Yggdrasil-2.0-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3-Yggdrasil-2.0-8B.Q4_1.gguf	Q4_1	4.78GB
Llama-3-Yggdrasil-2.0-8B.Q5_0.gguf	Q5_0	5.21GB
Llama-3-Yggdrasil-2.0-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3-Yggdrasil-2.0-8B.Q5_K.gguf	Q5_K	5.34GB
Llama-3-Yggdrasil-2.0-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3-Yggdrasil-2.0-8B.Q5_1.gguf	Q5_1	5.65GB
Llama-3-Yggdrasil-2.0-8B.Q6_K.gguf	Q6_K	6.14GB
Llama-3-Yggdrasil-2.0-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers tags: - mergekit - merge base_model: - Locutusque/Llama-3-NeuralHercules-5.0-8B - NousResearch/Meta-Llama-3-8B - NousResearch/Hermes-2-Theta-Llama-3-8B - Locutusque/llama-3-neural-chat-v2.2-8b model-index: - name: Llama-3-Yggdrasil-2.0-8B 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: 53.71 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Llama-3-Yggdrasil-2.0-8B 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: 26.92 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Llama-3-Yggdrasil-2.0-8B 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: 6.87 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Llama-3-Yggdrasil-2.0-8B 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: 1.68 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Llama-3-Yggdrasil-2.0-8B 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: 8.07 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Llama-3-Yggdrasil-2.0-8B 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: 24.07 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/Llama-3-Yggdrasil-2.0-8B 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 DARE TIES merge method using NousResearch/Meta-Llama-3-8B 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: NousResearch/Meta-Llama-3-8B
    # No parameters necessary for base model
  - model: NousResearch/Hermes-2-Theta-Llama-3-8B
    parameters:
      density: 0.6
      weight: 0.55
  - model: Locutusque/llama-3-neural-chat-v2.2-8b
    parameters:
      density: 0.55
      weight: 0.4
  - model: Locutusque/Llama-3-NeuralHercules-5.0-8B
    parameters:
      density: 0.65
      weight: 0.6
    
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	20.22
IFEval (0-Shot)	53.71
BBH (3-Shot)	26.92
MATH Lvl 5 (4-Shot)	6.87
GPQA (0-shot)	1.68
MuSR (0-shot)	8.07
MMLU-PRO (5-shot)	24.07