MarinaPlius
commited on
Commit
•
e46f1d4
1
Parent(s):
376fbaa
Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ tags:
|
|
16 |
# Salamandra 7B aligned EADOP Model Card
|
17 |
Salamandra 7B aligned EADOP is a full-finetuning version of
|
18 |
[BSC Language Technologies Unit](https://huggingface.co/BSC-LT)'s
|
19 |
-
[
|
20 |
model by the at the Barcelona Supercomputing Center focused on improving
|
21 |
the handling of out-of-domain Questions in a RAG instruction-following setting.
|
22 |
|
@@ -36,7 +36,7 @@ capability to politely and informatively refuse to answer questions that are out
|
|
36 |
---
|
37 |
|
38 |
## Model Details
|
39 |
-
Please refer to the [
|
40 |
for the specific details about the model architecture and pretraining.
|
41 |
|
42 |
## Intended Use
|
@@ -55,9 +55,9 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
55 |
import transformers
|
56 |
import torch
|
57 |
|
58 |
-
model_id = "
|
59 |
|
60 |
-
text = "
|
61 |
|
62 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
63 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
16 |
# Salamandra 7B aligned EADOP Model Card
|
17 |
Salamandra 7B aligned EADOP is a full-finetuning version of
|
18 |
[BSC Language Technologies Unit](https://huggingface.co/BSC-LT)'s
|
19 |
+
[Salamandra Instruct 7B](https://huggingface.co/BSC-LT/salamandra-7b-instruct)
|
20 |
model by the at the Barcelona Supercomputing Center focused on improving
|
21 |
the handling of out-of-domain Questions in a RAG instruction-following setting.
|
22 |
|
|
|
36 |
---
|
37 |
|
38 |
## Model Details
|
39 |
+
Please refer to the [Salamandra Instruct 7B model details](https://huggingface.co/BSC-LT/salamandra-7b-instruct#model-details)
|
40 |
for the specific details about the model architecture and pretraining.
|
41 |
|
42 |
## Intended Use
|
|
|
55 |
import transformers
|
56 |
import torch
|
57 |
|
58 |
+
model_id = "projecte-aina/salamandra-7b-aligned-EADOP"
|
59 |
|
60 |
+
text = "Quina és la finalitat del Servei Meterològic de Catalunya ?"
|
61 |
|
62 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
63 |
model = AutoModelForCausalLM.from_pretrained(
|