Documented Gensyn base
According to the model card and hub tags, the source is Gensyn/Qwen2.5-0.5B-Instruct, with hub tags confirming the finetune relationship.
Open Source Model Profile · Johnex
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-cunning_soft_robin
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-cunning_soft_robin is a 0.49B-parameter Qwen2 fine-tune from Johnex. Its model card records Gensyn/Qwen2.5-0.5B-Instruct as the base with TRL training.
- Publisher
- Johnex
- Task
- text-generation
- Model type
- qwen2
- License
- Unknown
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-cunning_soft_robin is published by Johnex as a qwen2-based text-generation fine-tune. The captured configuration identifies Qwen2ForCausalLM and Safetensors metadata reports 494032768 parameters. According to the model card, it fine-tunes Gensyn/Qwen2.5-0.5B-Instruct using TRL.
Recorded capabilities
TRL and GRPO workflow
According to the model card, training used TRL, with GRPO described as the method from the DeepSeekMath work; hub tags record grpo, rl-swarm, and trl.
Transformers quick start
According to the model card, a transformers pipeline example runs text-generation on this repository with a chat-style user message.
Qwen2 0.49B Transformers record
Captured config identifies Qwen2ForCausalLM and qwen2, with Safetensors metadata reporting 494032768 parameters and transformers library support.
Use cases in the source record
- Conversational text-generation experiments using the captured transformers pipeline setup for this repository.
- RL-swarm and GRPO research building on the documented Gensyn base and TRL workflow.
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: Johnex/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-cunning_soft_robin
Captured: Unknown. Processed: 2026-09-07T19:35:06.858250+00:00.
Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-cunning_soft_robin This model is a fine-tuned version of Gensyn/Qwen2.5-0.5B-Instruct . 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= "Johnex/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-cunning_soft_robin" , device= "cuda" ) output = generator([{ "role" : "user" , "content" : question}], max_new_tokens= 128 , return_full_text= False )[ 0 ] print (output[ "generated_text" ]) Tr…
F001F002F003F004F005F006F007F008F009F010F011F012F013