Delete README.me
Browse files
README.me
DELETED
|
@@ -1,49 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0 # Or the license of the original model
|
| 3 |
-
language: en
|
| 4 |
-
library_name: llama.cpp # Indicate it's primarily for llama.cpp ecosystem
|
| 5 |
-
tags:
|
| 6 |
-
- gguf
|
| 7 |
-
- quantized
|
| 8 |
-
- merge
|
| 9 |
-
- mergekit
|
| 10 |
-
- ties
|
| 11 |
-
- 12b
|
| 12 |
-
- text-generation
|
| 13 |
-
- etherealaurora
|
| 14 |
-
- mn-mag-mell
|
| 15 |
-
- nemomix
|
| 16 |
-
- chat
|
| 17 |
-
- roleplay
|
| 18 |
-
pipeline_tag: text-generation
|
| 19 |
-
base_model: TomoDG/EtherealAurora-MN-Nemo-12B
|
| 20 |
-
model_type: llama
|
| 21 |
-
---
|
| 22 |
-
|
| 23 |
-
# GGUF Quantized Models for TomoDG/EtherealAurora-MN-Nemo-12B
|
| 24 |
-
|
| 25 |
-
This repository contains GGUF format model files for [TomoDG/EtherealAurora-MN-Nemo-12B](https://huggingface.co/TomoDG/EtherealAurora-MN-Nemo-12B).
|
| 26 |
-
|
| 27 |
-
These files were quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp).
|
| 28 |
-
|
| 29 |
-
## Original Model Card
|
| 30 |
-
|
| 31 |
-
For details on the merge process, methodology, and intended use, please refer to the original model card:
|
| 32 |
-
[**TomoDG/EtherealAurora-MN-Nemo-12B**](https://huggingface.co/TomoDG/EtherealAurora-MN-Nemo-12B)
|
| 33 |
-
|
| 34 |
-
## Available Quantizations
|
| 35 |
-
|
| 36 |
-
| File Name | Quantization Type | Size (Approx) | Recommended RAM | Use Case |
|
| 37 |
-
| :------------------------------------------ | :---------------- | :------------ | :-------------- | :------------------------------------------- |
|
| 38 |
-
| `EtherealAurora-MN-Nemo-12B-Q4_K_S.gguf` | Q4_K_S | ~6.95 GB | 9 GB+ | Smallest 4-bit K-quant, lower RAM usage |
|
| 39 |
-
| `EtherealAurora-MN-Nemo-12B-Q4_K_M.gguf` | Q4_K_M | ~7.30 GB | 10 GB+ | Good balance quality/performance, medium RAM |
|
| 40 |
-
| `EtherealAurora-MN-Nemo-12B-Q5_K_M.gguf` | Q5_K_M | ~8.52 GB | 12 GB+ | Higher quality, higher RAM usage |
|
| 41 |
-
| `EtherealAurora-MN-Nemo-12B-Q6_K.gguf` | Q6_K | ~9.82 GB | 13 GB+ | Very high quality, close to FP16 |
|
| 42 |
-
| `EtherealAurora-MN-Nemo-12B-Q8_0.gguf` | Q8_0 | ~12.7 GB | 16 GB+ | Highest quality GGUF quant, large size | |
|
| 43 |
-
|
| 44 |
-
**General Recommendations:**
|
| 45 |
-
* **`_K_M` quants (like Q4_K_M, Q5_K_M):** Generally recommended for a good balance of quality and resource usage.
|
| 46 |
-
* **`Q6_K`:** Offers higher quality closer to FP16 if you have sufficient RAM.
|
| 47 |
-
* **`Q8_0`:** Highest quality GGUF quantization but requires the most resources.
|
| 48 |
-
|
| 49 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|