LLM EXPLORER 59,420 MODELS INDEXED

OpenELM 450M Instruct by apple

By apple · 798 downloads
HF Repo ↗ Copy URL

OpenELM 450M Instruct is an open-source language model by apple. Features: 450m LLM, VRAM: 0.9GB, License: apple-amlr, Instruction-Based, LLM Explorer Score: 0.13.

  Arxiv:2404.14619   Custom code   Instruct   Openelm   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/apple/OpenELM-450M-Instruct 

OpenELM 450M Instruct Parameters and Internals

Model Type 
Language Model
Use Cases 
Areas:
open research
Limitations:
No safety guarantees for outputs
Considerations:
Users should conduct thorough safety testing and implement appropriate filtering.
Additional Notes 
Supports pre-trained and instruction-tuned models with sizes varying from 270M to 3B parameters. Package includes data prep, training, fine-tuning, evaluation, checkpoints, and logs.
Training Details 
Data Sources:
RefinedWeb, deduplicated PILE, subset of RedPajama, subset of Dolma v1.6
Data Volume:
~1.8 trillion tokens
Methodology:
layer-wise scaling strategy within transformer layers
Input Output 
Input Format:
Plain text
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Use appropriate batch sizes and token speculation for faster generation.
LLM NameOpenELM 450M Instruct
Repository 🤗https://huggingface.co/apple/OpenELM-450M-Instruct 
Model Size450m
Required VRAM0.9 GB
Updated2026-07-23
Maintainerapple
Model Typeopenelm
Instruction-BasedYes
Model Files  0.9 GB
Model ArchitectureOpenELMForCausalLM
Licenseapple-amlr
Transformers Version4.39.3
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to OpenELM 450M Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...Databaes SFT DPO 4bitquantized0K / 0.3 GB90
...450M Instruct Databaes SFT DPO0K / 0.9 GB50
DPO Reference Model0K / 1.8 GB60