gonzalez-agirre
commited on
Commit
•
bdc4a9f
1
Parent(s):
bae5ed5
Update README.md
Browse files
README.md
CHANGED
@@ -51,7 +51,7 @@ This model card corresponds to the 2B instructed version.
|
|
51 |
To visit the model cards of other Salamandra versions, please refer to the [Model Index](#model-index).
|
52 |
|
53 |
The entire Salamandra family is released under a permissive [Apache 2.0 license]((https://www.apache.org/licenses/LICENSE-2.0)).
|
54 |
-
Along with the open weights, all training scripts and configuration files are made publicly available in [this GitHub repository](https://github.com/
|
55 |
|
56 |
> [!WARNING]
|
57 |
> **DISCLAIMER:** This model is a first proof-of-concept designed to demonstrate the instruction-following capabilities of recently released base models.
|
@@ -70,7 +70,7 @@ The pre-training corpus contains text in 35 European languages and code.
|
|
70 |
|
71 |
### Hyperparameters
|
72 |
|
73 |
-
The full list of hyperparameters for each model can be found [here](https://github.com/
|
74 |
|
75 |
### Architecture
|
76 |
|
@@ -156,7 +156,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
156 |
import transformers
|
157 |
import torch
|
158 |
|
159 |
-
model_id = "
|
160 |
|
161 |
text = "At what temperature does water boil?"
|
162 |
|
@@ -678,6 +678,6 @@ Technical report and paper coming soon.
|
|
678 |
## Model Index
|
679 |
|Model|Base|Instruct|
|
680 |
|:---:|:---:|:---:|
|
681 |
-
|2B| [Link](https://huggingface.co/
|
682 |
-
|7B| [Link](https://huggingface.co/
|
683 |
|40B| WiP | WiP |
|
|
|
51 |
To visit the model cards of other Salamandra versions, please refer to the [Model Index](#model-index).
|
52 |
|
53 |
The entire Salamandra family is released under a permissive [Apache 2.0 license]((https://www.apache.org/licenses/LICENSE-2.0)).
|
54 |
+
Along with the open weights, all training scripts and configuration files are made publicly available in [this GitHub repository](https://github.com/langtech-bsc/salamandra).
|
55 |
|
56 |
> [!WARNING]
|
57 |
> **DISCLAIMER:** This model is a first proof-of-concept designed to demonstrate the instruction-following capabilities of recently released base models.
|
|
|
70 |
|
71 |
### Hyperparameters
|
72 |
|
73 |
+
The full list of hyperparameters for each model can be found [here](https://github.com/langtech-bsc/salamandra/tree/main/configs).
|
74 |
|
75 |
### Architecture
|
76 |
|
|
|
156 |
import transformers
|
157 |
import torch
|
158 |
|
159 |
+
model_id = "BSC-LT/salamandra-2b-instruct"
|
160 |
|
161 |
text = "At what temperature does water boil?"
|
162 |
|
|
|
678 |
## Model Index
|
679 |
|Model|Base|Instruct|
|
680 |
|:---:|:---:|:---:|
|
681 |
+
|2B| [Link](https://huggingface.co/BSC-LT/salamandra-2b) | [Link](https://huggingface.co/BSC-LT/salamandra-2b-instruct) |
|
682 |
+
|7B| [Link](https://huggingface.co/BSC-LT/salamandra-7b) | [Link](https://huggingface.co/BSC-LT/salamandra-7b-instruct) |
|
683 |
|40B| WiP | WiP |
|