techwithsergiu/Qwen3.5-text-2B-bnb-4bit

docs: upd diagrams, new qwen-qlora-train, qwen35-toolkit links

docs: replace TBD fine-tuning section with qwen-qlora-train quick start

docs: add Conversion section linking qwen35-toolkit

Fixed quantization_config.llm_int8_skip_modules, to avoid re-quantizes embed_tokens layers on load

upd .gitattributes

upd visual tower info in readme

upd Model family in readme

upd Pipeline diagram in readme

add Pipeline diagram into readme

add rendered mermaid into readme

upd readme

restore .gitattributes

cleanup, add chat template

Upload a quantized Text-Only BNB 4-bit model

initial commit