You can deploy this model and start earning money today!

RichardErkhov/
Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf

Name: Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NIHAPPY-L3.1-8B-v0.09 - GGUF

Model creator: https://huggingface.co/Arkana08/
Original model: https://huggingface.co/Arkana08/NIHAPPY-L3.1-8B-v0.09/

Name	Quant method	Size
NIHAPPY-L3.1-8B-v0.09.Q2_K.gguf	Q2_K	2.96GB
NIHAPPY-L3.1-8B-v0.09.IQ3_XS.gguf	IQ3_XS	3.28GB
NIHAPPY-L3.1-8B-v0.09.IQ3_S.gguf	IQ3_S	3.43GB
NIHAPPY-L3.1-8B-v0.09.Q3_K_S.gguf	Q3_K_S	3.41GB
NIHAPPY-L3.1-8B-v0.09.IQ3_M.gguf	IQ3_M	3.52GB
NIHAPPY-L3.1-8B-v0.09.Q3_K.gguf	Q3_K	3.74GB
NIHAPPY-L3.1-8B-v0.09.Q3_K_M.gguf	Q3_K_M	3.74GB
NIHAPPY-L3.1-8B-v0.09.Q3_K_L.gguf	Q3_K_L	4.03GB
NIHAPPY-L3.1-8B-v0.09.IQ4_XS.gguf	IQ4_XS	4.18GB
NIHAPPY-L3.1-8B-v0.09.Q4_0.gguf	Q4_0	4.34GB
NIHAPPY-L3.1-8B-v0.09.IQ4_NL.gguf	IQ4_NL	4.38GB
NIHAPPY-L3.1-8B-v0.09.Q4_K_S.gguf	Q4_K_S	4.37GB
NIHAPPY-L3.1-8B-v0.09.Q4_K.gguf	Q4_K	4.58GB
NIHAPPY-L3.1-8B-v0.09.Q4_K_M.gguf	Q4_K_M	4.58GB
NIHAPPY-L3.1-8B-v0.09.Q4_1.gguf	Q4_1	4.78GB
NIHAPPY-L3.1-8B-v0.09.Q5_0.gguf	Q5_0	5.21GB
NIHAPPY-L3.1-8B-v0.09.Q5_K_S.gguf	Q5_K_S	5.21GB
NIHAPPY-L3.1-8B-v0.09.Q5_K.gguf	Q5_K	5.34GB
NIHAPPY-L3.1-8B-v0.09.Q5_K_M.gguf	Q5_K_M	5.34GB
NIHAPPY-L3.1-8B-v0.09.Q5_1.gguf	Q5_1	5.65GB
NIHAPPY-L3.1-8B-v0.09.Q6_K.gguf	Q6_K	6.14GB
NIHAPPY-L3.1-8B-v0.09.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: [] library_name: transformers tags:

mergekit
merge

(GGUF) Thanks mradermacher

GGUF: mradermacher/NIHAPPY-L3.1-8B-v0.09-GGUF
imatrix GGUF: mradermacher/NIHAPPY-L3.1-8B-v0.09-i1-GGUF

NIHAPPY a role-playing model that seamlessly integrates the finest qualities of various pre-trained language models. Crafted with a focus on dynamic storytelling, NIHAPPY thrives in creative and immersive roleplaying environments. It masterfully balances intricate reasoning with a smooth and consistent narrative flow, ensuring an engaging and coherent experience.

Merge Details

Merge Method

This model was created using the DARE TIES merge method, with v000000/L3.1-Niitorm-8B-DPO-t0.0001 serving as the base model. This approach ensures a fine-tuned balance between creativity, reasoning, and rule-following, ideal for intricate role-playing situations.

Models Merged

The following models were included in the merge:

Nitral-AI/Hathor_Tahsin-L3-8B-v0.85: Contributes to rule-following, consistency, and character accuracy.
v000000/L3.1-Niitorm-8B-DPO-t0.0001: A strong foundation for reasoning and logical responses.
v000000/L3-8B-Poppy-Moonfall-C: Focuses on storytelling, imagination, and creative expression.

Configuration

The following YAML configuration was used to produce NIHAPPY:

yaml

models:
  - model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
    parameters:
      weight: 0.35
      density: 0.65
  - model: v000000/L3-8B-Poppy-Moonfall-C
    parameters:
      weight: 0.45
      density: 0.65
  - model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.85
    parameters:
      weight: 0.20
      density: 0.68
merge_method: dare_ties
base_model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
parameters:
  int8_mask: true
dtype: bfloat16

Credits

Thanks to the creators of the models:

RichardErkhov/Arkana08_-_NIHAPPY-L3.1-8B-v0.09-gguf