nymtheescobar
commited on
Commit
•
7956074
1
Parent(s):
e5e618a
create readme file
Browse files
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- bn
|
4 |
+
- en
|
5 |
+
license: llama3
|
6 |
+
base_model: meta-llama/Meta-Llama-3.1-8B
|
7 |
+
---
|
8 |
+
|
9 |
+
# Bangla LLaMA 8B Bangla2B Base v0.1 [pre-trained]
|
10 |
+
|
11 |
+
Welcome to the inaugural release of the Bangla LLaMA 8B unolp-culturax base model – an important step in advancing LLMs for the Bangla language. This model is ready for immediate inference and is also primed for further fine-tuning to cater to your specific NLP tasks.
|
12 |
+
|
13 |
+
> **Please Note:** This model, labeled as a foundational Bangla Language Model (LLM), is designed primarily for Causal Language Modeling (LM) purposes. In other words, if you are looking for an instruction following model in Bangla, you may find [BanglaLLM/BanglaLLama-8b-unolp-culturax-instruct-v0.1]() more suitable for your needs.
|
14 |
+
|
15 |
+
## Model description
|
16 |
+
|
17 |
+
The Bangla LLaMA models have been enhanced and tailored specifically with an extensive Bangla vocabulary of 16,000 tokens, building upon the foundation set by the original LLaMA-3.
|
18 |
+
|
19 |
+
- **Model type:** A 8B parameter model for Causal LM pre-trained on unolp/culturax dataset.
|
20 |
+
- **Language(s):** Bangla and English
|
21 |
+
- **License:** GNU General Public License v3.0
|
22 |
+
- **Source Model:** [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
|
23 |
+
- **Training Precision:** `float16`
|
24 |
+
- **Code:** [GitHub](https://github.com/abhinand5/bangla-llama)
|
25 |
+
|
26 |
+
## Related Models
|
27 |
+
|
28 |
+
| Model | Type | Data | Base Model | # Params | Download Links |
|
29 |
+
|--------------------------|-----------------------------|-------------------|----------------------|------|------------------------------------------------------------------------|
|
30 |
+
| Bangla LLaMA 7B Base | Base model | 12GB | LLaMA 7B | 7B | [HF Hub](https://huggingface.co/BanglaLLM/bangla-llama-7b-base-v0.1) |
|
31 |
+
| Bangla LLaMA 13B Base | Base model | 4GB | LLaMA 13B | 13B | [HF Hub](https://huggingface.co/BanglaLLM/bangla-llama-13b-base-v0.1) |
|
32 |
+
| Bangla LLaMA 7B Instruct | Instruction following model | 145k instructions | Bangla LLaMA 7B Base | 7B | [HF Hub](https://huggingface.co/BanglaLLM/bangla-llama-7b-instruct-v0.1) |
|
33 |
+
| Bangla LLaMA 13B Instruct | Instruction following model | 145k instructions | Bangla LLaMA 13B Base | 13B | [HF Hub](BanglaLLM/bangla-llama-13b-instruct-v0.1) |
|
34 |
+
|
35 |
+
## Usage Note
|
36 |
+
|
37 |
+
It's important to note that the models have not undergone detoxification. Therefore, while they possess impressive linguistic capabilities, there is a possibility for them to generate content that could be deemed harmful or offensive. We urge users to exercise discretion and supervise the model's outputs closely, especially in public or sensitive applications.
|
38 |
+
|
39 |
+
## Meet the Developers
|
40 |
+
|
41 |
+
Get to know the creators behind this innovative model and follow their contributions to the field:
|
42 |
+
|
43 |
+
- [Abdullah Khan Zehady](https://www.linkedin.com/in/abdullah-khan-zehady-915ba024/)
|
44 |
+
|
45 |
+
## Citation
|
46 |
+
|
47 |
+
|
48 |
+
We hope this model serves as a valuable tool in your NLP toolkit and look forward to seeing the advancements it will enable in the understanding and generation of the Bangla language.
|