VladShash/deepseek-math-7b-lean-prover-dpo-olmo-3 download history
VladShash/deepseek-math-7b-lean-prover-dpo-olmo-3 is a 7.3B-parameter text generation model by VladShash. In the last 30 days it was downloaded 51 times (24 in the last 7 days), and 4,104 times in total.
It ranks #251,273 on the Hub by monthly downloads and #67,615 among text generation models.
It has 4 likes.
It is a fine-tune of formalmathatepfl/deepseek-math-7B-finetuned.
1 models build on deepseek-math-7b-lean-prover-dpo-olmo-3: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 371 times in the last 30 days. See the deepseek-math-7b-lean-prover-dpo-olmo-3 galaxy.
Most downloaded derivatives
- mradermacher/olmo-3-7b-lean-prover-dpo-GGUF (quantized), 320 downloads in 30 days
Open VladShash/deepseek-math-7b-lean-prover-dpo-olmo-3 on Hugging Face