gonzalez-agirre
commited on
Commit
•
90217fa
1
Parent(s):
82e163e
Update README.md
Browse files
README.md
CHANGED
@@ -51,7 +51,7 @@ This model card corresponds to the 2B 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 |
---
|
57 |
|
@@ -64,7 +64,7 @@ The pre-training corpus contains text in 35 European languages and code.
|
|
64 |
|
65 |
### Hyperparameters
|
66 |
|
67 |
-
The full list of hyperparameters for each model can be found [here](https://github.com/
|
68 |
|
69 |
### Architecture
|
70 |
|
@@ -150,7 +150,7 @@ pip install transformers torch accelerate sentencepiece protobuf
|
|
150 |
```python
|
151 |
from transformers import pipeline, set_seed
|
152 |
|
153 |
-
model_id = "
|
154 |
|
155 |
# Sample prompts
|
156 |
prompts = [
|
@@ -197,7 +197,7 @@ pip install transformers torch accelerate sentencepiece protobuf
|
|
197 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
198 |
import torch
|
199 |
|
200 |
-
model_id = "
|
201 |
|
202 |
# Input text
|
203 |
text = "El mercat del barri és"
|
@@ -241,7 +241,7 @@ pip install vllm
|
|
241 |
```python
|
242 |
from vllm import LLM, SamplingParams
|
243 |
|
244 |
-
model_id = "
|
245 |
|
246 |
# Sample prompts
|
247 |
prompts = [
|
@@ -747,6 +747,6 @@ Technical report and paper coming soon.
|
|
747 |
## Model Index
|
748 |
|Model|Base|Instruct|
|
749 |
|:---:|:---:|:---:|
|
750 |
-
|2B| [Link](https://huggingface.co/
|
751 |
-
|7B| [Link](https://huggingface.co/
|
752 |
|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/BSC-LT/salamandra).
|
55 |
|
56 |
---
|
57 |
|
|
|
64 |
|
65 |
### Hyperparameters
|
66 |
|
67 |
+
The full list of hyperparameters for each model can be found [here](https://github.com/langtech-bsc/salamandra/tree/main/configs).
|
68 |
|
69 |
### Architecture
|
70 |
|
|
|
150 |
```python
|
151 |
from transformers import pipeline, set_seed
|
152 |
|
153 |
+
model_id = "BSC-LT/salamandra-2b"
|
154 |
|
155 |
# Sample prompts
|
156 |
prompts = [
|
|
|
197 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
198 |
import torch
|
199 |
|
200 |
+
model_id = "BSC-LT/salamandra-2b"
|
201 |
|
202 |
# Input text
|
203 |
text = "El mercat del barri és"
|
|
|
241 |
```python
|
242 |
from vllm import LLM, SamplingParams
|
243 |
|
244 |
+
model_id = "BSC-LT/salamandra-2b"
|
245 |
|
246 |
# Sample prompts
|
247 |
prompts = [
|
|
|
747 |
## Model Index
|
748 |
|Model|Base|Instruct|
|
749 |
|:---:|:---:|:---:|
|
750 |
+
|2B| [Link](https://huggingface.co/BSC-LT/salamandra-2b) | [Link](https://huggingface.co/BSC-LT/salamandra-2b-instruct) |
|
751 |
+
|7B| [Link](https://huggingface.co/BSC-LT/salamandra-7b) | [Link](https://huggingface.co/BSC-LT/salamandra-7b-instruct) |
|
752 |
|40B| WiP | WiP |
|