uploaded readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Quantization made by Richard Erkhov.
|
| 2 |
+
|
| 3 |
+
[Github](https://github.com/RichardErkhov)
|
| 4 |
+
|
| 5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
| 6 |
+
|
| 7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
MFANN3bv0.6 - bnb 8bits
|
| 11 |
+
- Model creator: https://huggingface.co/netcat420/
|
| 12 |
+
- Original model: https://huggingface.co/netcat420/MFANN3bv0.6/
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
Original model description:
|
| 18 |
+
---
|
| 19 |
+
library_name: transformers
|
| 20 |
+
license: apache-2.0
|
| 21 |
+
datasets:
|
| 22 |
+
- netcat420/MFANN
|
| 23 |
+
pipeline_tag: text-classification
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
MFANN 3b version 0.6
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
fine-tuned on the MFANN dataset as it stands on 5/2/2024 as it is an ever changing and expaning dataset.
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
benchmark results for this 3b model:
|
| 38 |
+
|
| 39 |
+
64.34 <-- Average
|
| 40 |
+
62.63 <-- Arc
|
| 41 |
+
77.1 <-- HellaSwag
|
| 42 |
+
58.43 <-- MMLU
|
| 43 |
+
51.71 <-- TruthfulQA
|
| 44 |
+
74.66 <-- Winogrande
|
| 45 |
+
61.49 <-- GSM8K
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
currently the worlds best 2.78B parameter model!!!!!!!!!!! as of 5/2/2024
|
| 49 |
+
|