Pinkstack
/

Superthoughts-lite-v1

Text Generation

text-generation-inference

Model card Files Files and versions

Pinkstack commited on Feb 15

Commit

c8890a9

·

verified ·

1 Parent(s): 0b27704

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ pipeline_tag: text-generation
 # Information
 Advanced, high-quality and **lite** reasoning for a tiny size that you can run on your phone.
-At original quality, it runs at ~300 tokens/second on a single a800 Nvidia GPU.
 Trained similarly to Deepseek R1, we used Smollm2 as a base model, then we've SFT fine tuned on reasoning using our own private superthoughts instruct dataset & modified the tokenizer slightly, after the SFT fine tuning we used GRPO to further amplify it's mathematics & problem solving abilities.

 # Information
 Advanced, high-quality and **lite** reasoning for a tiny size that you can run on your phone.
+At original quality, it runs at ~400 tokens/second on a single H100 Nvidia GPU from Friendli.
 Trained similarly to Deepseek R1, we used Smollm2 as a base model, then we've SFT fine tuned on reasoning using our own private superthoughts instruct dataset & modified the tokenizer slightly, after the SFT fine tuning we used GRPO to further amplify it's mathematics & problem solving abilities.