LLM EXPLORER 67,627 MODELS INDEXED

Safelm 1.7B by locuslab

By locuslab · 55 downloads

Safelm 1.7B is an open-source language model by locuslab. Features: 600b LLM, VRAM: 9.7GB, Context: 8K, License: mit, LLM Explorer Score: 0.17.

  Arxiv:2504.16980 Dataset:huggingfacetb/smollm-c... Dataset:locuslab/moral educati...   Dataset:locuslab/refuseweb   Dataset:locuslab/safeweb   Llama   Model   Pytorch   Region:us   Safety p   Smollm2
Model Card on HF πŸ€—: https://huggingface.co/locuslab/safelm-1.7b 

Safelm 1.7B Parameters and Internals

LLM NameSafelm 1.7B
Repository πŸ€—https://huggingface.co/locuslab/safelm-1.7b 
Model Namelocuslab/safelm-1.7b_rephrase_refusal_moral_ed_600B
Model Size600b
Required VRAM9.7 GB
Updated2026-10-02
Maintainerlocuslab
Model Typellama
Model Files  9.7 GB
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to Safelm 1.7B

Best Alternatives
Context / RAM
Downloads
Likes
Baguettotron 600M2K / 1.2 GB19625
Llama 600M Rus2K / 2.2 GB233
Note: green Score (e.g. "73.2") means that the model is better than locuslab/safelm-1.7b.