Róger Nascimento Santos
commited on
Commit
•
1df3f80
1
Parent(s):
1fb1a13
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,9 +5,13 @@ datasets:
|
|
| 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.
|
|
|
|
| 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 |
+
|
| 9 |
it's not perfect in portuguese, but in the perfect point to train a bit more for specific task in this language.
|
| 10 |
+
|
| 11 |
consider check the jupyter notebooks in the files section for more info.
|
| 12 |
+
|
| 13 |
these notebooks were get from web and it's very similar to "cabrita" model, that was made on top of llama1.
|
| 14 |
|
| 15 |
trained in only 120 steps and with some results very similar to VMware/open-llama-13b-open-instruct
|
| 16 |
+
|
| 17 |
maybe necessary to adjust the parameters of inference to make it work better.
|