KillerShoaib
commited on
Commit
•
bcdb43f
1
Parent(s):
7d6a6bd
Update README.md
Browse files
README.md
CHANGED
@@ -28,6 +28,12 @@ inference: false
|
|
28 |
# 4-bit Quantization
|
29 |
**This is 4-bit quantization of Llama-3 8b model.**
|
30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
# Model Details
|
32 |
|
33 |
**Llama 3 8 billion** model was finetuned using **unsloth** package on a **cleaned Bangla alpaca** dataset. After that the model was quantized in **4-bit**. The model is finetuned for **2 epoch** on a single T4 GPU.
|
|
|
28 |
# 4-bit Quantization
|
29 |
**This is 4-bit quantization of Llama-3 8b model.**
|
30 |
|
31 |
+
|
32 |
+
# Llama-3 Bangla Different Formats
|
33 |
+
|
34 |
+
- `LoRA Adapters only` - [**KillerShoaib/llama-3-8b-bangla-lora**](https://huggingface.co/KillerShoaib/llama-3-8b-bangla-lora)
|
35 |
+
- `GGUF q4_k_m` - [**KillerShoaib/llama-3-8b-bangla-GGUF-Q4_K_M**](https://huggingface.co/KillerShoaib/llama-3-8b-bangla-GGUF-Q4_K_M)
|
36 |
+
|
37 |
# Model Details
|
38 |
|
39 |
**Llama 3 8 billion** model was finetuned using **unsloth** package on a **cleaned Bangla alpaca** dataset. After that the model was quantized in **4-bit**. The model is finetuned for **2 epoch** on a single T4 GPU.
|