Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: v000000/L3.1-Niitorm-8B-DPO-t0.0001
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- merge
|
| 6 |
+
- llama
|
| 7 |
+
- dpo
|
| 8 |
+
- llama-cpp
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# L3.1-Niitorm-8B-DPO-t0.0001 (GGUFs)
|
| 12 |
+
This model was converted to GGUF format from [`v000000/L3.1-Niitorm-8B-DPO-t0.0001`](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001) using llama.cpp.
|
| 13 |
+
Refer to the [original model card](https://huggingface.co/v000000/L3.1-Niitorm-8B-DPO-t0.0001) for more details on the model.
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# Ordered by quality:
|
| 18 |
+
* q8_0 imatrix --- 14.2g
|
| 19 |
+
* q6_k imatrix --- 11.2g
|
| 20 |
+
* q5_k_s imatrix --- 9.48g
|
| 21 |
+
* iq4_xs imatrix --- 7.44g
|
| 22 |
+
|
| 23 |
+
<i>imatrix data (V2 - 287kb) randomized bartowski, kalomeze groups, ERP/RP snippets, working gpt4 code, toxic qa, human messaging, randomized posts, story, novels</i>
|