rityak_-_L3.1-HermesBreakGradient-8B-gguf

RichardErkhov/rityak_-_L3.1-HermesBreakGradient-8B-gguf

rityak_-_L3.1-HermesBreakGradient-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

155

4% of all-time downloads

All-time downloads

3.7K

Public

Repo size

92.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf103 GB · 100%

At a glance

Access: Public
Created: Oct 11, 2024
Updated: Oct 11, 2024
SHA: 6adbcfce

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3.1-HermesBreakGradient-8B - GGUF

Model creator: https://huggingface.co/rityak/
Original model: https://huggingface.co/rityak/L3.1-HermesBreakGradient-8B/

Name	Quant method	Size
L3.1-HermesBreakGradient-8B.Q2_K.gguf	Q2_K	2.96GB
L3.1-HermesBreakGradient-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
L3.1-HermesBreakGradient-8B.IQ3_S.gguf	IQ3_S	3.43GB
L3.1-HermesBreakGradient-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
L3.1-HermesBreakGradient-8B.IQ3_M.gguf	IQ3_M	0.77GB
L3.1-HermesBreakGradient-8B.Q3_K.gguf	Q3_K	2.39GB
L3.1-HermesBreakGradient-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
L3.1-HermesBreakGradient-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
L3.1-HermesBreakGradient-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
L3.1-HermesBreakGradient-8B.Q4_0.gguf	Q4_0	4.34GB
L3.1-HermesBreakGradient-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
L3.1-HermesBreakGradient-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
L3.1-HermesBreakGradient-8B.Q4_K.gguf	Q4_K	4.58GB
L3.1-HermesBreakGradient-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
L3.1-HermesBreakGradient-8B.Q4_1.gguf	Q4_1	4.78GB
L3.1-HermesBreakGradient-8B.Q5_0.gguf	Q5_0	5.21GB
L3.1-HermesBreakGradient-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
L3.1-HermesBreakGradient-8B.Q5_K.gguf	Q5_K	5.34GB
L3.1-HermesBreakGradient-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
L3.1-HermesBreakGradient-8B.Q5_1.gguf	Q5_1	5.65GB
L3.1-HermesBreakGradient-8B.Q6_K.gguf	Q6_K	6.14GB
L3.1-HermesBreakGradient-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

NousResearch/Hermes-3-Llama-3.1-8B
rityak/L3.1-FormaxGradient
rityak/L3.1-HermesBreak-8B
Sao10K/Llama-3.1-8B-Stheno-v3.4 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 DARE TIES merge method using rityak/L3.1-FormaxGradient 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: rityak/L3.1-FormaxGradient
  - model: NousResearch/Hermes-3-Llama-3.1-8B
    parameters:
      density: 0.2
      weight: 0.1
  - model: Sao10K/Llama-3.1-8B-Stheno-v3.4
    parameters:
      density: 0.5
      weight: 0.3
  - model: rityak/L3.1-HermesBreak-8B
    parameters:
      density: 0.8
      weight: 0.6
merge_method: dare_ties
base_model: rityak/L3.1-FormaxGradient
parameters:
  normalize: false
  int8_mask: true
dtype: float32
out_dtype: bfloat16

Created: Oct 11, 2024
Updated: Oct 11, 2024