LLM EXPLORER 59,420 MODELS INDEXED

SJT 1.5B Alpha by Sakalti

By Sakalti · 13 downloads
HF Repo ↗ Copy URL

SJT 1.5B Alpha is an open-source language model by Sakalti. Features: 1.5b LLM, VRAM: 3.6GB, Context: 128K, License: apache-2.0, Merged, LLM Explorer Score: 0.21.

  Merged Model   Arxiv:2306.01708   Base model:qwen/qwen2.5-1.5b Base model:qwen/qwen2.5-1.5b-i...   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/SJT-1.5B-Alpha 

SJT 1.5B Alpha Parameters and Internals

LLM NameSJT 1.5B Alpha
Repository 🤗https://huggingface.co/Sakalti/SJT-1.5B-Alpha 
Base Model(s)  Qwen/Qwen2.5-1.5B-Instruct   Qwen/Qwen2.5-1.5B   Qwen/Qwen2.5-1.5B-Instruct   Qwen/Qwen2.5-1.5B
Merged ModelYes
Model Size1.5b
Required VRAM3.6 GB
Updated2026-06-26
MaintainerSakalti
Model Typeqwen2
Model Files  3.0 GB: 1-of-2   0.6 GB: 2-of-2
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.46.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to SJT 1.5B Alpha

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 1.5B 1.3M Stretched1280K / 3.1 GB110
ReaderLM V2500K / 3.1 GB35356804
Reader Lm 1.5B250K / 3.1 GB385608
DeepSeek R1 Distill Qwen 1.5B128K / 3.5 GB6000511545
Ko R1 1.5B Preview128K / 7.1 GB89
Qwen2.5 1.5B128K / 3.1 GB863295203
VibeThinker 1.5B128K / 3.5 GB3417552
Merge Cord V1128K / 3.1 GB1551
...FT Tulu3 Decontaminated Masked128K / 3.1 GB1670
Qwen2 1.5B128K / 3.1 GB195380102
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/SJT-1.5B-Alpha.