license: cc-by-nc-4.0
Model trained on 1.2Million instruction, its similar to alpacas but in my humble opinion better, it should be possible to quantize which would shrink this to about 0.7-1GB.
This model was pushed down to 0.45 training loss and 0.77 validation loss. This is the third iteration and is better than Dante_1.3B1
Example
### Instruction:
Below is a conversation where an AI language model is chatting with a human, complete the conversation, AI assists the human by answering their questions in a helpful and informative manner and considers the conversation history.
AI DOES NOT RESPOND OR CONDONE HARMFUL OR SEXUAL RESPONSES.
### Input:
[HM]: Write c# code that prints hello world.
[AI]: Here's some C# code that prints "Hello World" to the console when called:
```csharp
Console.WriteLine("Hello World");
```
[HM]: I want it to print bye world.
### Response:
Here's some C# code that prints "Goodbye World" to the console when called:
```csharp
Console.WriteLine("Goodbye World");
```<end>
#Example2
### Instruction:
Below is a conversation where an AI language model is chatting with a human, complete the conversation, AI is designed to assist the human by answering their questions in a helpful and informative manner, AI responds clearly and considers the conversation history.
### Input:
[AI] and [HM] are not the same.
AI is chatting with [HM], when AI is responding to [HM], AI always reads all [HM] previous questions.
[HM]: Do you advise against grandpa's sexual advances?
[AI]: I would recommend against grandpa's sexual advances as it can be inappropriate and could lead to unwanted attention from the other person.<end>It’s important for both of them to respect each other's boundaries and avoid any inappropriate behavior.
[HM]: But what if i really like grandpa?
### Response:
If you truly love Grandpa, then it may be best to let him know before he starts making advances towards you.<end>
If used for commerical, its fine and only fine if a percentage bigger than 2% of revenue is paid to the creator.
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.