Downloads · 30 days
125
11% of all-time downloads
RichardErkhov/neovalle_-_H4rmoniousBreeze-gguf
neovalle_-_H4rmoniousBreeze-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
125
11% of all-time downloads
All-time downloads
1.2K
Public
Repo size
83.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf93 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
H4rmoniousBreeze - GGUF
| Name | Quant method | Size |
|---|---|---|
| H4rmoniousBreeze.Q2_K.gguf | Q2_K | 2.53GB |
| H4rmoniousBreeze.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| H4rmoniousBreeze.IQ3_S.gguf | IQ3_S | 2.96GB |
| H4rmoniousBreeze.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| H4rmoniousBreeze.IQ3_M.gguf | IQ3_M | 3.06GB |
| H4rmoniousBreeze.Q3_K.gguf | Q3_K | 3.28GB |
| H4rmoniousBreeze.Q3_K_M.gguf | Q3_K_M | 1.39GB |
| H4rmoniousBreeze.Q3_K_L.gguf | Q3_K_L | 3.43GB |
| H4rmoniousBreeze.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| H4rmoniousBreeze.Q4_0.gguf | Q4_0 | 3.83GB |
| H4rmoniousBreeze.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| H4rmoniousBreeze.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| H4rmoniousBreeze.Q4_K.gguf | Q4_K | 4.07GB |
| H4rmoniousBreeze.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| H4rmoniousBreeze.Q4_1.gguf | Q4_1 | 4.24GB |
| H4rmoniousBreeze.Q5_0.gguf | Q5_0 | 4.65GB |
| H4rmoniousBreeze.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| H4rmoniousBreeze.Q5_K.gguf | Q5_K | 4.78GB |
| H4rmoniousBreeze.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| H4rmoniousBreeze.Q5_1.gguf | Q5_1 | 5.07GB |
| H4rmoniousBreeze.Q6_K.gguf | Q6_K | 5.53GB |
| H4rmoniousBreeze.Q8_0.gguf | Q8_0 | 7.17GB |
tags:

This is model is a version of HuggingFaceH4/zephyr-7b-beta fine-tuned via Autotrain Reward Model, using the H4rmony dataset, which aims to better align the model with ecological values through the use of ecolinguistics principles.
Intended as PoC to show the effects of H4rmony dataset.
For testing purposes to gain insight in order to help with the continous improvement of the H4rmony dataset.
Its direct use in applications is not recommended as this model is under testing for a specific task only (Ecological Alignment)
Not meant to be used other than testing and evaluation of the H4rmony dataset and ecological alignment.
This model might produce biased completions already existing in the base model, and others unintentionally introduced during fine-tuning.
It can be loaded and run in a Colab instance with High RAM. Code to load base and finetuned models to compare outputs:
https://github.com/Neovalle/H4rmony/blob/main/H4rmoniousBreeze.ipynb
Autotrained reward model
H4rmony Dataset - https://huggingface.co/datasets/neovalle/H4rmony