models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
LLaDA-Instruct-JustGRPO-GSM8Ke2d2-gsm8k-finetune-Qwen3-2Bsimcse-large-gsm8kgsm8k-mdlmllama3.18binstruct-gsm8k-lora-step-continuation-5epochsgsm8k-rephraser-7bqwen25-math-1.5b-gsm8k-lora-step-continuation-5epochsqwen25-math-1.5b-gsm8k-lora-correctness-5epochsllama3.18binstruct-gsm8k-lora-correctness-5epochsgemma29bit-gsm8k-lora-correctness-2epochsgsm8k-bd3lm-s16gsm8k-arllama2-7b-gsm8k-valuemmlu-gsm8k-rephraser-scaling-13bqwen25-math-1.5b-gsm8k-lora-correctness-10epochsqwen25-math-7b-gsm8k-lora-correctness-5epochsgemma29bit-gsm8k-lora-step-continuation-2epochsgemma29bit-gsm8k-lora-step-continuation-5epochsgsm8k-bd3lm-s4gemma29bit-gsm8k-lora-correctness-5epochsgsm8k-bd3lm-s8e2d2-gsm8k-finetune-Qwen3-2B-TESTqwen25-math-7b-gsm8k-lora-step-continuation-5epochsgsm8k-rephraser-13be2d2-gsm8k-finetune-Qwen3-2Bqwen25-math-1.5b-gsm8k-lora-correctness-2epochsqwen25-math-1.5b-gsm8k-lora-step-continuation-10epochsqwen25-math-7b-gsm8k-lora-step-continuation-2epochsqwen25-math-7b-gsm8k-lora-correctness-2epochsqwen25-math-7b-gsm8k-lora-correctness-10epochs