Quantization made by Richard Erkhov.

Top-Western-Maid-7B - GGUF

Model creator: https://huggingface.co/saishf/
Original model: https://huggingface.co/saishf/Top-Western-Maid-7B/

Name	Quant method	Size
Top-Western-Maid-7B.Q2_K.gguf	Q2_K	2.53GB
Top-Western-Maid-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Top-Western-Maid-7B.IQ3_S.gguf	IQ3_S	2.96GB
Top-Western-Maid-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Top-Western-Maid-7B.IQ3_M.gguf	IQ3_M	3.06GB
Top-Western-Maid-7B.Q3_K.gguf	Q3_K	3.28GB
Top-Western-Maid-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Top-Western-Maid-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Top-Western-Maid-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Top-Western-Maid-7B.Q4_0.gguf	Q4_0	3.83GB
Top-Western-Maid-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Top-Western-Maid-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Top-Western-Maid-7B.Q4_K.gguf	Q4_K	4.07GB
Top-Western-Maid-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Top-Western-Maid-7B.Q4_1.gguf	Q4_1	4.24GB
Top-Western-Maid-7B.Q5_0.gguf	Q5_0	4.65GB
Top-Western-Maid-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Top-Western-Maid-7B.Q5_K.gguf	Q5_K	4.78GB
Top-Western-Maid-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Top-Western-Maid-7B.Q5_1.gguf	Q5_1	5.07GB
Top-Western-Maid-7B.Q6_K.gguf	Q6_K	5.53GB
Top-Western-Maid-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-4.0 tags: - mergekit - merge base_model: - NeverSleep/Noromaid-7B-0.4-DPO - Undi95/Toppy-M-7B - mistralai/Mistral-7B-v0.1 - senseable/WestLake-7B-v2 model-index: - name: Top-Western-Maid-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 69.37 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 87.4 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 64.63 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 58.79 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 83.27 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 65.96 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B 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 mistralai/Mistral-7B-v0.1 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: mistralai/Mistral-7B-v0.1
    # No parameters necessary for base model
  - model: senseable/WestLake-7B-v2
    parameters:
      density: 0.53
      weight: 0.55
  - model: NeverSleep/Noromaid-7B-0.4-DPO
    parameters:
      density: 0.53
      weight: 0.30  
  - model: Undi95/Toppy-M-7B
    parameters:
      density: 0.53
      weight: 0.15  
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.57
AI2 Reasoning Challenge (25-Shot)	69.37
HellaSwag (10-Shot)	87.40
MMLU (5-Shot)	64.63
TruthfulQA (0-shot)	58.79
Winogrande (5-shot)	83.27
GSM8k (5-shot)	65.96