LLM EXPLORER 59,358 MODELS INDEXED

Sparsing Law 0.1B Relu by SparseLLM

By SparseLLM · 7 downloads
HF Repo ↗ Copy URL

Sparsing Law 0.1B Relu is an open-source language model by SparseLLM. Features: 2b LLM, VRAM: 0.4GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.15.

  Arxiv:2411.02335   Custom code   En   Pytorch   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/SparseLLM/sparsing-law-0.1b-relu 

Sparsing Law 0.1B Relu Parameters and Internals

LLM NameSparsing Law 0.1B Relu
Repository 🤗https://huggingface.co/SparseLLM/sparsing-law-0.1b-relu 
Model Size2b
Required VRAM0.4 GB
Updated2026-07-29
MaintainerSparseLLM
Model Files  0.4 GB   0.4 GB
Supported Languagesen zh
Model ArchitectureMiniCPMForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size122753
Torch Data Typebfloat16

Best Alternatives to Sparsing Law 0.1B Relu

Best Alternatives
Context / RAM
Downloads
Likes
MiniCPM 2B 128K64K / 6 GB190544
MiniCPM 2B Sft Bf164K / 5.5 GB66563126
MiniCPM MoE 8x2B4K / 27.7 GB137346
MiniCPM Duplex4K / 5.5 GB4906
...iCPM 2B RAFT Lora Hotpotqa Dev4K / 5.5 GB60
...iniCPM 2B DPO Bf16 Safetensors4K / 5.5 GB751
...iniCPM 2B DPO Fp32 Safetensors4K / 10.9 GB551
...iniCPM 2B Sft Fp32 Safetensors4K / 10.9 GB341
...iniCPM 2B Sft Fp32 Safetensors4K / 10.9 GB71
...iniCPM 2B DPO Bf16 Safetensors4K / 5.5 GB11
Note: green Score (e.g. "73.2") means that the model is better than SparseLLM/sparsing-law-0.1b-relu.