Commit
·
4e0afc1
1
Parent(s):
3526e49
Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ I have released the new data [Code-74k-ShareGPT](https://huggingface.co/datasets
|
|
| 22 |
Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 42 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.
|
| 23 |
|
| 24 |
|
| 25 |
-
This is a full fine tuned model. Links for quantized models
|
| 26 |
|
| 27 |
|
| 28 |
**GPTQ GGUF & AWQ**
|
|
@@ -33,6 +33,8 @@ GGUF: [Link](https://huggingface.co/TheBloke/Code-13B-GGUF)
|
|
| 33 |
|
| 34 |
AWQ: [Link](https://huggingface.co/TheBloke/Code-13B-AWQ)
|
| 35 |
|
|
|
|
|
|
|
| 36 |
|
| 37 |
**Example Prompt:**
|
| 38 |
```
|
|
|
|
| 22 |
Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 42 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.
|
| 23 |
|
| 24 |
|
| 25 |
+
This is a full fine tuned model. Links for quantized models are given below.
|
| 26 |
|
| 27 |
|
| 28 |
**GPTQ GGUF & AWQ**
|
|
|
|
| 33 |
|
| 34 |
AWQ: [Link](https://huggingface.co/TheBloke/Code-13B-AWQ)
|
| 35 |
|
| 36 |
+
Extremely thankful to [TheBloke](https://huggingface.co/TheBloke) for making Quantized versions of model.
|
| 37 |
+
|
| 38 |
|
| 39 |
**Example Prompt:**
|
| 40 |
```
|