Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Essacheez

Qwen2.5-3B-RG-SFT-Fact-No-Repeat

Qwen2.5-3B-RG-SFT-Fact-No-Repeat is a 3.09B-parameter Qwen2 text-generation fine-tune from Essacheez. According to the model card, it was finetuned from unsloth/Qwen2.5-3B-Instruct with Apache-2.0 licensing.

Publisher
Essacheez
Task
text-generation
Model type
qwen2
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

The model is published by Essacheez as a Qwen2 text-generation model. The captured configuration identifies Qwen2ForCausalLM, and Safetensors metadata reports 3,085,938,688 parameters. According to the model card, it was finetuned from unsloth/Qwen2.5-3B-Instruct and training used Unsloth with Hugging Face TRL.

Recorded capabilities

Documented Unsloth lineage

According to the model card, the model was finetuned from unsloth/Qwen2.5-3B-Instruct; hub tags repeat that finetune linkage.

Unsloth plus TRL training note

According to the model card, this Qwen2 model was trained 2x faster with Unsloth and Hugging Face TRL.

Apache-2.0 license

Card data records apache-2.0, and hub tags include a license:apache-2.0 entry.

Use cases in the source record

  • Conversational text-generation work using the Transformers stack recorded for this Qwen2 fine-tune.
  • Unsloth and TRL SFT workflow reuse where the documented unsloth/Qwen2.5-3B-Instruct lineage is relevant.

Limitations and unknowns

  • No evaluation results, context-window value, or hardware requirements were extracted.
  • Training detail beyond the Unsloth and TRL note and named source model was not extracted.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Essacheez/Qwen2.5-3B-RG-SFT-Fact-No-Repeat

Captured: Unknown. Processed: 2026-09-07T19:35:39.262772+00:00.

Uploaded model Developed by: Essacheez License: apache-2.0 Finetuned from model : unsloth/Qwen2.5-3B-Instruct This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

F001F002F003F004F005F006F007F008F009F010F011