Qwen2.5-Coder lineage
According to the model card, it was finetuned from unsloth/qwen2.5-coder-3b-instruct-bnb-4bit.
Open Source Model Profile · RushabhShah122000
qwen25-coder-3b-python-expert-16bit
qwen25-coder-3b-python-expert-16bit is a 3.09B-parameter Qwen2 text-generation fine-tune from RushabhShah122000. According to the model card, it derives from a Qwen2.5-Coder Unsloth checkpoint.
- Publisher
- RushabhShah122000
- Task
- text-generation
- Model type
- qwen2
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
qwen25-coder-3b-python-expert-16bit is published by RushabhShah122000 as a transformers text-generation model. The captured configuration identifies Qwen2ForCausalLM with qwen2 type, and Safetensors metadata reports 3085938688 parameters. According to the model card, it was finetuned from unsloth/qwen2.5-coder-3b-instruct-bnb-4bit.
Recorded capabilities
3.09B Qwen2 config
Safetensors metadata reports 3085938688 parameters with Qwen2ForCausalLM architecture and qwen2 model type.
Unsloth and TRL note
According to the model card, training used Unsloth with Huggingface's TRL library and is described as 2x faster.
Apache-2.0 Transformers record
Captured metadata records apache-2.0 licensing with transformers library support.
Use cases in the source record
- Conversational text-generation workflows using transformers or text-generation-inference-compatible runtimes.
- Python-focused coder experiments building on the publisher-noted Qwen2.5-Coder lineage, subject to validation of the specialization claim.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- Finetuning dataset, steps, and Python-specialization details were not extracted beyond the publisher lineage note.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: RushabhShah122000/qwen25-coder-3b-python-expert-16bit
Captured: Unknown. Processed: 2026-09-07T19:35:51.502551+00:00.
Uploaded finetuned model Developed by: RushabhShah122000 License: apache-2.0 Finetuned from model : unsloth/qwen2.5-coder-3b-instruct-bnb-4bit This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
F001F002F003F004F005F006F007F008F009F010F011