Commit
•
cd10896
1
Parent(s):
7b86a4a
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ pipeline_tag: text-generation
|
|
| 18 |
|
| 19 |
## Model Details
|
| 20 |
|
| 21 |
-
CataLlama-Base is a fine-tune of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the [catallama/Catalan-Raw-Text](https://huggingface.co/datasets/catallama/Catalan-Raw-Text) raw Catalan corpus dataset
|
| 22 |
|
| 23 |
The model shows improved proficiency with the Catalan language.
|
| 24 |
|
|
@@ -59,7 +59,7 @@ print(outputs[0]["generated_text"][len(prompt):])
|
|
| 59 |
|
| 60 |
## Training procedure
|
| 61 |
|
| 62 |
-
The model was trained without a prompt template
|
| 63 |
|
| 64 |
Example:
|
| 65 |
|
|
|
|
| 18 |
|
| 19 |
## Model Details
|
| 20 |
|
| 21 |
+
**CataLlama-Base** is a fine-tune of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the [catallama/Catalan-Raw-Text](https://huggingface.co/datasets/catallama/Catalan-Raw-Text) raw Catalan corpus dataset
|
| 22 |
|
| 23 |
The model shows improved proficiency with the Catalan language.
|
| 24 |
|
|
|
|
| 59 |
|
| 60 |
## Training procedure
|
| 61 |
|
| 62 |
+
The model was trained **without a prompt template**, only with raw text separated by BOS and EOS tokens.
|
| 63 |
|
| 64 |
Example:
|
| 65 |
|