license: apache-2.0
language:
- en
pipeline_tag: text-generation
datasets:
- appvoid/no-prompt-15k
palmer
a better base model
palmer is a series of ~1b parameters language models fine-tuned to be used as base models instead of using custom prompts for tasks. This means that it can be further fine-tuned on more data with custom prompts as usual or be used for downstream tasks as any base model you can get. The model has the best of both worlds: some "bias" to act as an assistant, but also the abillity to predict the next-word from its internet knowledge base. It's a 1.1b llama 2 model so you can use it with your favorite tools/frameworks.
evaluation
| Model | ARC_C | HellaSwag | PIQA | Winogrande |
|---|---|---|---|---|
| tinyllama-2 | 0.2807 | 0.5463 | 0.7067 | 0.5683 |
| palmer-001 | 0.2807 | 0.5524 | 0.7106 | 0.5896 |
| tinyllama-2.5 | 0.3191 | 0.5896 | 0.7307 | 0.5872 |
| tinyllama-3 | 0.3029 | 0.5935 | 0.7329 | 0.5959 |
| palmer-002 | 0.3242 | 0.5956 | 0.7345 | 0.5888 |
This model shows exceptional performance and as of now is the best tinyllama-size base model. Furthermore, this proves LIMA paper point and serves as a good open-source alternative to openai's babbage-002.
training
Training took ~3.5 P100 gpu hours. It was trained on 15,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.
prompt
no prompt
