π§
Qwen3.5 4b Mathcodesearch Sdpo E Step30 model by ipfipfipf
β 39
π¬Technical Deep Dive
Full Specifications [+]
π Updated daily
Source summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Model Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
π Identity & Source
- id
- hf-model--ipfipfipf--qwen3.5-4b-mathcodesearch-sdpo-e-step30
- slug
- ipfipfipf--qwen3.5-4b-mathcodesearch-sdpo-e-step30
- source
- huggingface
- author
- ipfipfipf
- license
- Apache-2.0
- tags
- qwen3.5, megatron-core, sdpo, reinforcement-learning, math, code, search, text-generation, base_model:qwen/qwen3.5-4b, base_model:finetune:qwen/qwen3.5-4b, license:apache-2.0, region:us
βοΈ Technical Specs
- params billions
- 4
- context length
- 4,096
- pipeline tag
- text-generation
- vram gb
- 4.3
- vram is estimated
- true
- vram formula
- VRAM β (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)
π Engagement & Metrics
- downloads
- 0
Data indexed from public sources. Updated daily.