Math fine-tune pair
According to the model card, this fine-tunes ZMC2019/Qwen2.5-Math-7B-Instruct on the open-r1/OpenR1-Math-220k dataset; Hub tags list the same dataset and base-model entries.
Open Source Model Profile · ZMC2019
Qwen7B-Math-L28
Qwen7B-Math-L28 is a 7.62B-parameter Qwen2 text-generation fine-tune from ZMC2019. According to the model card, it fine-tunes ZMC2019/Qwen2.5-Math-7B-Instruct on the open-r1/OpenR1-Math-220k dataset using TRL with SFT.
- Publisher
- ZMC2019
- Task
- text-generation
- Model type
- qwen2
- License
- Unknown
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Qwen7B-Math-L28 is published by ZMC2019 as a Qwen2 text-generation fine-tune. The captured configuration identifies Qwen2ForCausalLM with model type qwen2, and Safetensors metadata reports 7,615,616,512 parameters. According to the model card, it fine-tunes ZMC2019/Qwen2.5-Math-7B-Instruct on the open-r1/OpenR1-Math-220k dataset using TRL.
Recorded capabilities
TRL with SFT
According to the model card, training used TRL with supervised fine-tuning, and Hub tags record trl, sft, and generated_from_trainer.
Pipeline quickstart
According to the model card, a Transformers text-generation pipeline snippet shows chat-style inference with this model.
Use cases in the source record
- Math-focused text generation building on the OpenR1-Math-220k fine-tuning described in the model card.
- Conversational question-answering workflows using the Transformers text-generation pipeline shown in the model card.
Limitations and unknowns
- No license value was extracted from this record.
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: ZMC2019/Qwen7B-Math-L28
Captured: Unknown. Processed: 2026-09-07T19:35:17.598779+00:00.
Model Card for Qwen7B-Math-L28 This model is a fine-tuned version of ZMC2019/Qwen2.5-Math-7B-Instruct on the open-r1/OpenR1-Math-220k dataset. It has been trained using TRL . Quick start from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline( "text-generation" , model= "ZMC2019/Qwen7B-Math-L28" , device= "cuda" ) output = generator([{ "role" : "user" , "content" : question}], max_new_tokens= 128 , return_full_text= False )[ 0 ] print (output[ "generated_text" ]) Training procedure This model was…
F001F002F003F004F005F006F008F009F010F011F012F013