LLM EXPLORER 59,182 MODELS INDEXED

Cerebras GPT 111M Instruction by SebastianSchramm

By SebastianSchramm · 11 downloads
HF Repo ↗ Copy URL

Cerebras GPT 111M Instruction is an open-source language model by SebastianSchramm. Features: 111m LLM, VRAM: 0.4GB, Instruction-Based, LLM Explorer Score: 0.11, Arc: 24.4, HellaSwag: 26.1, MMLU: 25.9.

Base model:cerebras/cerebras-g... Base model:finetune:cerebras/c...   Cerebras   En   Gpt2   Instruct   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/SebastianSchramm/Cerebras-GPT-111M-instruction 

Cerebras GPT 111M Instruction Parameters and Internals

Model Type 
Instruction fine-tuned, Text generation
Supported Languages 
en (Fluent)
Training Details 
Data Sources:
alpaca_gpt4_data, alpaca_data_cleaned
Methodology:
Instruction fine-tuning
Input Output 
Input Format:
Formatted input according to the Stanford Alpaca prompt template is recommended
Accepted Modalities:
text
Performance Tips:
Format input according to the provided prompt template during inference for best results.
LLM NameCerebras GPT 111M Instruction
Repository 🤗https://huggingface.co/SebastianSchramm/Cerebras-GPT-111M-instruction 
Base Model(s)  Cerebras GPT 111M   cerebras/Cerebras-GPT-111M
Model Size111m
Required VRAM0.4 GB
Updated2026-08-06
MaintainerSebastianSchramm
Model Typegpt2
Instruction-BasedYes
Model Files  0.4 GB   0.5 GB
Supported Languagesen
Model ArchitectureGPT2LMHeadModel
Model Max Length2048
Transformers Version4.33.0.dev0
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50258
Torch Data Typefloat32
Activation Functiongelu
Errorsreplace