LLM EXPLORER 60,277 MODELS INDEXED

Pretrained SCP 1B QLoRA by AiAF

By AiAF · 8 downloads
HF Repo ↗ Copy URL

Pretrained SCP 1B QLoRA is an open-source language model by AiAF. Features: 1b LLM, VRAM: 2.5GB, Context: 128K, Instruction-Based, LLM Explorer Score: 0.17.

Base model:aiaf/pretrained-ada... Base model:finetune:aiaf/pretr... Dataset:aiaf/scpwiki-archive-0...   Instruct   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/AiAF/Pretrained-SCP-1B-QLoRA 

Pretrained SCP 1B QLoRA Parameters and Internals

LLM NamePretrained SCP 1B QLoRA
Repository 🤗https://huggingface.co/AiAF/Pretrained-SCP-1B-QLoRA 
Base Model(s)  meta-llama/Llama-3.2-1B-Instruct   AiAF/Pretrained-Adapter-SCP-1B-QLoRA   meta-llama/Llama-3.2-1B-Instruct   AiAF/Pretrained-Adapter-SCP-1B-QLoRA
Model Size1b
Required VRAM2.5 GB
Updated2026-09-04
MaintainerAiAF
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.49.0
Tokenizer ClassPreTrainedTokenizer
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Pretrained SCP 1B QLoRA

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 1B Instruct128K / 2.5 GB212072100
Llama 3.2 1B Instruct128K / 2.5 GB101146341549
...1B Claude Opus Fable5 Thinking128K / 2.2 GB6165166
LlaMa3.2 1B Instruct128K / 4.9 GB140
Llama3.2 1B CoT128K / 2.5 GB6321
Llama 3.2 1B Instruct Bf16128K / 2.5 GB5105
Llama 3.2 1B Instruct128K / 2.5 GB200
...Claude Opus Fable5 V2 Thinking128K / 2.2 GB2884
Llama3.2 1B Manumit V1128K / 2.5 GB1320
Llama 3.2 Mavrick.Spark 1B128K / 2.5 GB2372
Note: green Score (e.g. "73.2") means that the model is better than AiAF/Pretrained-SCP-1B-QLoRA.