|
--- |
|
license: apache-2.0 |
|
base_model: |
|
- BAAI/Infinity-Instruct-7M-Gen-mistral-7B |
|
- SanjiWatsuki/Kunoichi-7B |
|
- uukuguy/speechless-instruct-mistral-7b-v0.2 |
|
base_model_relation: merge |
|
--- |
|
|
|
Test merge of 7b models for learning purposees. |
|
|
|
Description: |
|
This model is a merge of BAAI/Infinity-Instruct-7M-Gen-mistral-7B, SanjiWatsuki/Kunoichi-7B, and uukuguy/speechless-instruct-mistral-7b-v0.2 |
|
This is the first model I've ever uploaded and wanted to learn more about the process. Merged using mergekit-moe. |
|
|
|
Works up to 8k context, 16k with 2.5 RoPe scaling |
|
|
|
Prompt template: Custom format, or Alpaca |
|
|
|
Alpaca: |
|
Below is an instruction that describes a task. Write a response that appropriately completes the request. |
|
|
|
### Instruction: |
|
{prompt} |
|
|
|
### Response: |
|
|
|
|
|
|
