Downloads · 30 days
22
9% of all-time downloads
athirdpath_-_Harmonia-20B-gguf
RichardErkhov/athirdpath_-_Harmonia-20B-gguf
athirdpath_-_Harmonia-20B-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.
All-time downloads
242
Public
Repo size
223 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf258 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 2, 2024
- Updated
- Jun 2, 2024
- SHA
- d65bfabd
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Harmonia-20B - GGUF
- Model creator: https://huggingface.co/athirdpath/
- Original model: https://huggingface.co/athirdpath/Harmonia-20B/
| Name | Quant method | Size |
|---|---|---|
| Harmonia-20B.Q2_K.gguf | Q2_K | 6.91GB |
| Harmonia-20B.IQ3_XS.gguf | IQ3_XS | 7.63GB |
| Harmonia-20B.IQ3_S.gguf | IQ3_S | 8.06GB |
| Harmonia-20B.Q3_K_S.gguf | Q3_K_S | 8.06GB |
| Harmonia-20B.IQ3_M.gguf | IQ3_M | 8.53GB |
| Harmonia-20B.Q3_K.gguf | Q3_K | 9.04GB |
| Harmonia-20B.Q3_K_M.gguf | Q3_K_M | 9.04GB |
| Harmonia-20B.Q3_K_L.gguf | Q3_K_L | 9.9GB |
| Harmonia-20B.IQ4_XS.gguf | IQ4_XS | 10.01GB |
| Harmonia-20B.Q4_0.gguf | Q4_0 | 7.19GB |
| Harmonia-20B.IQ4_NL.gguf | IQ4_NL | 10.57GB |
| Harmonia-20B.Q4_K_S.gguf | Q4_K_S | 10.59GB |
| Harmonia-20B.Q4_K.gguf | Q4_K | 11.22GB |
| Harmonia-20B.Q4_K_M.gguf | Q4_K_M | 11.22GB |
| Harmonia-20B.Q4_1.gguf | Q4_1 | 11.67GB |
| Harmonia-20B.Q5_0.gguf | Q5_0 | 12.83GB |
| Harmonia-20B.Q5_K_S.gguf | Q5_K_S | 12.83GB |
| Harmonia-20B.Q5_K.gguf | Q5_K | 13.18GB |
| Harmonia-20B.Q5_K_M.gguf | Q5_K_M | 13.18GB |
| Harmonia-20B.Q5_1.gguf | Q5_1 | 13.98GB |
| Harmonia-20B.Q6_K.gguf | Q6_K | 15.28GB |
| Harmonia-20B.Q8_0.gguf | Q8_0 | 19.79GB |
Original model description:
license: cc-by-nc-4.0
Description
This is a unified 20B model crafted via a multi-step SLERP merge of eight 20B models. The aim was to develop a versatile "base model" for TaskArithmetic in this size class.
Merging Process:
Models:
- model: Undi95/Emerhyst-20B
- model: Undi95/MXLewd-L2-20B
- model: Undi95/Lewd-Sydney-20B
- model: athirdpath/Nethena-20b-Glued
- model: tavtav/Rose-20B
- model: Undi95/PsyMedRP-v1-20B
- model: NeverSleep/Noromaid-20b-v0.1.1
- model: Undi95/U-Amethyst-20B
Concept:
The idea behind this process was to blend the unique attributes of each model while minimizing individual quirks. This approach has also shown promising results as a standalone RP model, providing a combination of high-quality writing and situational problem-solving/awareness.
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Thanks to Undi95 for pioneering the 20B recipe, and for most of the models involved.
- Created
- Jun 2, 2024
- Updated
- Jun 2, 2024