You can deploy this model and start earning money today!

RichardErkhov/
kotyKD_-_Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B-gguf

Name: kotyKD_-_Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B - GGUF

Model creator: https://huggingface.co/kotyKD/
Original model: https://huggingface.co/kotyKD/Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B/

Name	Quant method	Size
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q2_K.gguf	Q2_K	2.96GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.IQ3_S.gguf	IQ3_S	3.43GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.IQ3_M.gguf	IQ3_M	3.52GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q3_K.gguf	Q3_K	3.74GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q4_0.gguf	Q4_0	4.34GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q4_K.gguf	Q4_K	4.58GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q4_1.gguf	Q4_1	4.78GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q5_0.gguf	Q5_0	5.21GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q5_K.gguf	Q5_K	5.34GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q5_1.gguf	Q5_1	5.65GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q6_K.gguf	Q6_K	6.14GB
Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

arcee-ai/Llama-3.1-SuperNova-Lite
NousResearch/Hermes-3-Llama-3.1-8B
unsloth/Meta-Llama-3.1-8B library_name: transformers tags:
mergekit
merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using unsloth/Meta-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

---
models:
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      weight: 1
      density: 2
  - model: NousResearch/Hermes-3-Llama-3.1-8B
    parameters:
      weight: 1
      density: 1.3
merge_method: ties
base_model: unsloth/Meta-Llama-3.1-8B
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16

RichardErkhov/kotyKD_-_Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B-gguf