Commit
•
acb7575
1
Parent(s):
e37d567
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
datasets:
|
| 5 |
+
- tatsu-lab/alpaca
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
base_model:
|
| 9 |
+
- nickypro/tinyllama-15M
|
| 10 |
+
pipeline_tag: text-generation
|
| 11 |
+
library_name: transformers
|
| 12 |
+
metrics:
|
| 13 |
+
- accuracy
|
| 14 |
+
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
[](https://hf.co/QuantFactory)
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
# QuantFactory/tinyllama-15M-alpaca-finetuned-GGUF
|
| 21 |
+
This is quantized version of [elvinmarkmv/tinyllama-15M-alpaca-finetuned](https://huggingface.co/elvinmarkmv/tinyllama-15M-alpaca-finetuned) created using llama.cpp
|
| 22 |
+
|
| 23 |
+
# Original Model Card
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
Loss: 2.371992
|