You can deploy this model and start earning money today!

RichardErkhov/
lemon07r_-_llama-3-NeuralMahou-8b-gguf

Name: lemon07r_-_llama-3-NeuralMahou-8b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-NeuralMahou-8b - GGUF

Model creator: https://huggingface.co/lemon07r/
Original model: https://huggingface.co/lemon07r/llama-3-NeuralMahou-8b/

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

Original model description:

license: llama3 library_name: transformers tags:

mergekit
merge base_model:
mlabonne/NeuralDaredevil-8B-abliterated
nbeerbower/llama-3-spicy-abliterated-stella-8B
flammenai/Mahou-1.2-llama3-8B model-index:
name: llama-3-NeuralMahou 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: 67.41 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou 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: 83.45 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou 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: 68.63 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou 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: 58.21 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou 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: 77.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou 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: 72.55 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lemon07r/llama-3-NeuralMahou name: Open LLM Leaderboard

NeuralMahou

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 mlabonne/NeuralDaredevil-8B-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: mlabonne/NeuralDaredevil-8B-abliterated
dtype: bfloat16
merge_method: model_stock
slices:
- sources:
  - layer_range: [0, 32]
    model: flammenai/Mahou-1.2-llama3-8B
  - layer_range: [0, 32]
    model: nbeerbower/llama-3-spicy-abliterated-stella-8B
  - layer_range: [0, 32]
    model: mlabonne/NeuralDaredevil-8B-abliterated

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.33
AI2 Reasoning Challenge (25-Shot)	67.41
HellaSwag (10-Shot)	83.45
MMLU (5-Shot)	68.63
TruthfulQA (0-shot)	58.21
Winogrande (5-shot)	77.74
GSM8k (5-shot)	72.55

RichardErkhov/lemon07r_-_llama-3-NeuralMahou-8b-gguf