nymtheescobar
commited on
Commit
•
cf8fc96
1
Parent(s):
bd14995
Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ language:
|
|
4 |
- en
|
5 |
license: llama3.1
|
6 |
base_model:
|
7 |
-
-
|
8 |
datasets:
|
9 |
- BanglaLLM/bangla-alpaca-orca
|
10 |
tags:
|
@@ -16,7 +16,7 @@ tags:
|
|
16 |
- Transformer
|
17 |
---
|
18 |
|
19 |
-
# Bangla LLaMA-3.1 8B Bangla-Alpaca-Orca Instruct v0.1 [finetune]
|
20 |
|
21 |
Welcome to the inaugural release of the Bangla LLaMA-3.1 8B bangla-alpaca-orca instruct model – an important step in advancing LLMs for the Bangla language. This model is ready for immediate inference.
|
22 |
|
@@ -24,6 +24,8 @@ Welcome to the inaugural release of the Bangla LLaMA-3.1 8B bangla-alpaca-orca i
|
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
|
|
27 |
- **Model type:** A 8B parameter model for Causal LM instruct finetuned with BanglaLLM/bangla-alpaca-orca.
|
28 |
- **Language(s):** Bangla and English
|
29 |
- **License:** GNU General Public License v3.0
|
|
|
4 |
- en
|
5 |
license: llama3.1
|
6 |
base_model:
|
7 |
+
- meta-llama/Llama-3.1-8B
|
8 |
datasets:
|
9 |
- BanglaLLM/bangla-alpaca-orca
|
10 |
tags:
|
|
|
16 |
- Transformer
|
17 |
---
|
18 |
|
19 |
+
# Bangla LLaMA-3.1 8B Bangla-Alpaca-Orca Instruct v0.1 [no-pretrain-finetune]
|
20 |
|
21 |
Welcome to the inaugural release of the Bangla LLaMA-3.1 8B bangla-alpaca-orca instruct model – an important step in advancing LLMs for the Bangla language. This model is ready for immediate inference.
|
22 |
|
|
|
24 |
|
25 |
## Model description
|
26 |
|
27 |
+
In this model we didn't done the pretraining on uonlp/Culturax dataset rather than we did the direct finetunning with bangla-alpaca-orca using Meta LLama 3.1 8b as base model.
|
28 |
+
|
29 |
- **Model type:** A 8B parameter model for Causal LM instruct finetuned with BanglaLLM/bangla-alpaca-orca.
|
30 |
- **Language(s):** Bangla and English
|
31 |
- **License:** GNU General Public License v3.0
|