Hugging Face's logo

mpasila
/
Viking-SlimSonnet-v1-LoRA-7B

PEFT
Safetensors
Transformers
text-generation-inference
unsloth
llama
trl
Model card Files Community

This is the fully trained version (with fixed formatting!!).

Dataset used: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned which was further filtered to remove prompts/examples that are longer than 4076 tokens (removed about 385 examples).

Prompt format is: ChatML

Merged model: mpasila/Viking-SlimSonnet-v1-7B

Trained with regular LoRA (not quantized/QLoRA) and LoRA rank was 128 and Alpha set to 32. Trained for 1 epoch using A40 for about 23 hours.

Uploaded model

  • Developed by: mpasila
  • License: apache-2.0
  • Finetuned from model : LumiOpen/Viking-7B

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
6
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for mpasila/Viking-SlimSonnet-v1-LoRA-7B

Base model

LumiOpen/Viking-7B
Adapter
(9)
this model

Datasets used to train mpasila/Viking-SlimSonnet-v1-LoRA-7B