Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · GreenNode

GreenMind-Medium-14B-R1

GreenMind-Medium-14B-R1 is a 14.77B-parameter Qwen2 Vietnamese reasoning fine-tune from GreenNode built on Qwen2.5-14B-Instruct.

Publisher
GreenNode
Task
text-generation
Model type
qwen2
License
mit
Library
Unknown
Publication status
Accepted · not indexed

Model overview

GreenMind-Medium-14B-R1 is published by GreenNode as a Qwen2 text-generation fine-tune aimed at Vietnamese reasoning questions. The captured configuration identifies Qwen2ForCausalLM and Safetensors metadata reports 14,770,033,664 parameters. According to the model card, it fine-tunes Qwen/Qwen2.5-14B-Instruct with Group Relative Policy Optimization, and card data records mit licensing.

Recorded capabilities

Vietnamese reasoning fine-tune

According to the model card, this is a medium-sized Vietnamese language model for intermediate-level reasoning across general knowledge, mathematics, and natural and social science topics, fine-tuned with Group Relative Policy Optimization.

131K-token context record

According to the model card, context length is 131,072 tokens with 8,192 tokens of generation.

Publisher-reported Vietnamese benchmarks

According to the model card, comparison tables cover SeaExam-style sets and a VMLU set where the model averages 74.29, alongside per-task Vietnamese figures; all scores are publisher-reported.

Documented Transformers quickstart

According to the model card, a quickstart snippet loads the model with AutoModelForCausalLM and AutoTokenizer using apply_chat_template.

Use cases in the source record

  • Vietnamese question answering on general knowledge, mathematics, and science topics using the documented chat-template quickstart.
  • Vietnamese benchmark comparison work that reuses the card's reported SeaExam and VMLU tables as publisher-supplied reference points.

Limitations and unknowns

  • Benchmark tables are publisher-reported comparisons against named public and private models; Ethen has not independently measured these scores.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: GreenNode/GreenMind-Medium-14B-R1

Captured: Unknown. Processed: 2026-09-07T19:35:05.807839+00:00.

GreenMind-Medium-14B-R1 We release GreenMind-Medium-14B-R1 , a medium-sized Vietnamese language model capable of effectively addressing questions that require intermediate-level reasoning, such as general knowledge, mathematics, natural science and social science topics. By leveraging the Group Relative Policy Optimization strategy for fine-tuning, we guide the model to generate logically coherent responses. Model Description Model Type: Causal Language Models Base Model: Qwen/Qwen2.5-14B-Instruct Parameters: 14.7B Context Length: Full 131,072 tokens and generation 8192 tokens Language: Vietnamese Quickstart Here provides a code sni…

F001F002F003F004F005F006F007F009F010F011F012F013F014F018F019