LLM EXPLORER 57,918 MODELS INDEXED

DeepSeek R1 Distill Qwen 1.5B GSPO Basic by leonMW

By leonMW · 9 downloads
HF Repo ↗ Copy URL

DeepSeek R1 Distill Qwen 1.5B GSPO Basic is an open-source language model by leonMW. Features: 1.5b LLM, VRAM: 3.5GB, Context: 128K, LLM Explorer Score: 0.2.

  Arxiv:2402.03300 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Endpoints compatible   Generated from trainer   Grpo   Qwen2   Region:us   Safetensors   Trl
Model Card on HF 🤗: https://huggingface.co/leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic 

DeepSeek R1 Distill Qwen 1.5B GSPO Basic Parameters and Internals

LLM NameDeepSeek R1 Distill Qwen 1.5B GSPO Basic
Repository 🤗https://huggingface.co/leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic 
Model NameDeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic
Base Model(s)  deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B   deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Model Size1.5b
Required VRAM3.5 GB
Updated2026-07-22
MaintainerleonMW
Model Typeqwen2
Model Files  3.5 GB   0.0 GB
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.57.1
Tokenizer ClassLlamaTokenizerFast
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size151936

Best Alternatives to DeepSeek R1 Distill Qwen 1.5B GSPO Basic

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 1.5B 1.3M Stretched1280K / 3.1 GB310
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
VibeThinker 1.5B128K / 3.5 GB3417552
Qwen2.5 1.5B128K / 3.1 GB863295203
...FT Tulu3 Decontaminated Masked128K / 3.1 GB1670
Seq Monkey Pretrain Base 1.5B128K / 3.5 GB370
Qwen2 1.5B128K / 3.1 GB195380102
Note: green Score (e.g. "73.2") means that the model is better than leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic.