LLM EXPLORER 65,695 MODELS INDEXED

TactLM Math ProcessGRPO Qwen2.5 0.5B by zaydsyed

By zaydsyed · 579 downloads
HF Repo ↗ Copy URL

TactLM Math ProcessGRPO Qwen2.5 0.5B is an open-source language model by zaydsyed. Features: 0.5b LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Instruction-Based.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-0.5b-i...   Conversational   Dataset:ai-mo/numinamath-cot Dataset:eleutherai/hendrycks m...   Dataset:openai/gsm8k Dataset:zaydsyed/tactlm-math-r...   En   Endpoints compatible   Grpo   Instruct   Math   Process-reward   Qwen2   Region:us   Rlvr   Safetensors
Model Card on HF 🤗: https://huggingface.co/zaydsyed/TactLM-Math-ProcessGRPO-Qwen2.5-0.5B 

TactLM Math ProcessGRPO Qwen2.5 0.5B Parameters and Internals

LLM NameTactLM Math ProcessGRPO Qwen2.5 0.5B
Repository 🤗https://huggingface.co/zaydsyed/TactLM-Math-ProcessGRPO-Qwen2.5-0.5B 
Base Model(s)  Qwen/Qwen2.5-0.5B-Instruct   Qwen/Qwen2.5-0.5B-Instruct
Model Size0.5b
Required VRAM1 GB
Updated2026-10-27
Maintainerzaydsyed
Model Typeqwen2
Instruction-BasedYes
Model Files  1.0 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version5.19.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to TactLM Math ProcessGRPO Qwen2.5 0.5B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 0.5B Abyme Merge3128K / 1.3 GB511
Qwen2 0.5B Abyme Merge2128K / 0.3 GB450
Qwen2.5 0.5B Instruct64K / 1 GB160
Qwen2.5 0.5B Instruct32K / 1 GB6324790572
Switchboard Router 0.5B32K / 1 GB5102
Qwen2.5 0.5B Abliterated32K / 1.3 GB14501
Seger Qwen2.5 0.5B32K / 1 GB5990
Oss Jev Qwen05 Decision 10K32K / 1 GB2510
Qwen2.5 0.5B Grounded Sft32K / 1 GB7281
Qwen2.5 0.5B Grounded Rloo32K / 1 GB7051
Note: green Score (e.g. "73.2") means that the model is better than zaydsyed/TactLM-Math-ProcessGRPO-Qwen2.5-0.5B.