Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
| 4 |
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
```
|
| 7 |
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
| 8 |
|
|
@@ -13,7 +21,7 @@ Below is an instruction that describes a task. Write a response that appropriate
|
|
| 13 |
```
|
| 14 |
|
| 15 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 16 |
-
|
| 17 |
```
|
| 18 |
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
| 19 |
base_model_config: mistralai/Mistral-7B-Instruct-v0.1
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
# Mistral-7B-code-16k-qlora
|
| 5 |
|
| 6 |
+
I'm excited to announce the release of a new model called Mistral-7B-code-16k-qlora. This small and fast model shows a lot of promise for supporting coding or acting as a copilot. I'm currently looking for people to help me test it out!
|
| 7 |
+
|
| 8 |
+
## Additional Information
|
| 9 |
+
|
| 10 |
+
This model was trained on 3x RTX 3090 in my homelab, using around 130kWh for approximately 23 cents, which is equivalent to around $30 for electricity.
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
## Prompt template: Alpaca
|
| 14 |
```
|
| 15 |
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
| 16 |
|
|
|
|
| 21 |
```
|
| 22 |
|
| 23 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 24 |
+
## Settings:
|
| 25 |
```
|
| 26 |
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
| 27 |
base_model_config: mistralai/Mistral-7B-Instruct-v0.1
|