LLM EXPLORER 57,252 MODELS INDEXED

StepFun Formalizer 7B by stepfun-ai

By stepfun-ai · 841 downloads
HF Repo ↗ Copy URL

StepFun Formalizer 7B is an open-source language model by stepfun-ai. Features: 7b LLM, VRAM: 15.3GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.21.

  Arxiv:2508.04440 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Chat   Conversational Dataset:stepfun-ai/stepfun-for...   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/stepfun-ai/StepFun-Formalizer-7B 

StepFun Formalizer 7B Parameters and Internals

LLM NameStepFun Formalizer 7B
Repository 🤗https://huggingface.co/stepfun-ai/StepFun-Formalizer-7B 
Base Model(s)  DeepSeek R1 Distill Qwen 7B   deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Model Size7b
Required VRAM15.3 GB
Updated2026-08-08
Maintainerstepfun-ai
Model Typeqwen2
Model Files  13.2 GB: 1-of-2   2.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to StepFun Formalizer 7B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Preview986K / 15.2 GB100
Qwen2.5 7B Instruct 1M986K / 15.4 GB52534373
Hush Qwen2.5 7B V1.2986K / 15.2 GB41
Hush Qwen2.5 7B V1.1986K / 15.2 GB51
Hush Qwen2.5 7B V1.4986K / 15.2 GB81
Hush Qwen2.5 7B Preview986K / 15.2 GB50
Hush Qwen2.5 7B V1.3986K / 15.2 GB102
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB102
Qwen 2.5 7B Exp Sce986K / 15.2 GB102
Qwen2.5 7B MixStock V0.1986K / 15.2 GB63
Note: green Score (e.g. "73.2") means that the model is better than stepfun-ai/StepFun-Formalizer-7B.