cubby
In this repository, we propose the next iteration of palmer, a new family of small language models trained with better foundational models, better data but same tasks: Text rewriting, paraphrasing, tone transfer, grammar-style editing, and instruction-following text transformations. With only 90m parameters, this model is perfect for experiments on small SBCs and low-power devices.
Our custom evaluation consists of 100 text-editing tasks where the model has to modify a diversity of texts in different ways. All models were evaluated using q8_0 gguf quantization.
ModelAvgEmbStringTokenRuleExactStrictFlaggedParams
🥇 nano84.7095.8181.1278.2287.5739/10068/10019/10090m
lfm272.0493.1962.0056.2275.3521/10040/10035/100700m
granite471.9692.5465.0154.9876.4117/10034/10033/100350m
qwen351.8187.7645.2633.6550.806/10022/10060/100600m
The model has learned from a dataset with about 1 million examples on how to edit text in many different ways. The dataset contains high-quality data that was further expanded using common well-known heuristics.
supportersBuy Me A Coffee
legalIf you are an individual, you're totally free to make money with the model as long as you properly credit the model being used in your products. If you are a company, you need to get a license at this email for commercial purposes.
Note: the model has not been tested as a chat assistant and it might not work as intended, use with caution.

Model	Avg	Emb	String	Token	Rule	Exact	Strict	Flagged	Params
`🥇 nano`	84.70	95.81	81.12	78.22	87.57	39/100	68/100	19/100	90m
`lfm2`	72.04	93.19	62.00	56.22	75.35	21/100	40/100	35/100	700m
`granite4`	71.96	92.54	65.01	54.98	76.41	17/100	34/100	33/100	350m
`qwen3`	51.81	87.76	45.26	33.65	50.80	6/100	22/100	60/100	600m

appvoid/palmer-005

supporters

legal

appvoid/
palmer-005