Róger Nascimento Santos
commited on
Commit
•
1fb1a13
1
Parent(s):
82f69a2
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Gustrd/dolly-15k-libretranslate-pt
|
| 5 |
+
library_name: peft
|
| 6 |
---
|
| 7 |
+
this adapter model using (peft) was made on top of openlm-research/open_llama_3b_v2 (https://huggingface.co/openlm-research/open_llama_3b_v2)
|
| 8 |
+
it's not perfect in portuguese, but in the perfect point to train a bit more for specific task in this language.
|
| 9 |
+
consider check the jupyter notebooks in the files section for more info.
|
| 10 |
+
these notebooks were get from web and it's very similar to "cabrita" model, that was made on top of llama1.
|
| 11 |
+
|
| 12 |
+
trained in only 120 steps and with some results very similar to VMware/open-llama-13b-open-instruct
|
| 13 |
+
maybe necessary to adjust the parameters of inference to make it work better.
|