|
--- |
|
base_model: LumiOpen/Viking-7B |
|
language: |
|
- en |
|
- fi |
|
- sv |
|
- 'no' |
|
- da |
|
- is |
|
- nn |
|
license: apache-2.0 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- llama |
|
- trl |
|
- sft |
|
datasets: |
|
- Gryphe/Sonnet3.5-SlimOrcaDedupCleaned |
|
- mpasila/Sonnet3.5-SlimOrcaDedupCleaned-4k-context |
|
--- |
|
This is a test model because the previous attempt failed. So it turns out I also trained this incorrectly due to the dataset using wrongly formatted ShareGPT so after I trained it again "correctly" for another full epoch I noticed that so.. I will have to train it yet again.. but at least now it should be fixed. But this model is using the wrongly formatted dataset. The next model should be better. |
|
|
|
Prompt format is: ChatML |
|
|
|
LoRA: [mpasila/Viking-SlimSonnet-v0.2-LoRA-7B](https://huggingface.co/mpasila/Viking-SlimSonnet-v0.2-LoRA-7B) |
|
|
|
Trained with regular LoRA (not quantized/QLoRA) and LoRA rank was 128 and Alpha set to 32. Trained for 5000 steps (0.11 epoch). |
|
|
|
# Uploaded model |
|
|
|
- **Developed by:** mpasila |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** LumiOpen/Viking-7B |
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|