LLM EXPLORER 66,291 MODELS INDEXED

Dense E1 Seq2048 Gbs128 10B by JIRU-W

By JIRU-W · 110 downloads

Dense E1 Seq2048 Gbs128 10B is an open-source language model by JIRU-W. Features: 10b LLM, VRAM: 1.1GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.3.

  Custom code Dataset:jiru-w/olmoe-mix-0924-...   Dense   Mask moe   Olmoe   Region:us   Research   Safetensors

Dense E1 Seq2048 Gbs128 10B Parameters and Internals

LLM NameDense E1 Seq2048 Gbs128 10b
Repository πŸ€—https://huggingface.co/JIRU-W/dense_e1_seq2048_gbs128_10b 
Model Size10b
Required VRAM1.1 GB
Updated2026-10-31
MaintainerJIRU-W
Model Typemask_moe
Model Files  1.1 GB
Model ArchitectureMaskMoeForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version5.20.1
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|padding|>
Vocabulary Size50304