techwithsergiu/Qwen3.5-9B-bnb-4bit

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

docs: split fine-tuning into text LoRA (qwen-qlora-train) and VLM paths

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

add Pipeline diagram into readme

add rendered mermaid into readme

upd readme

More accurate config.json

Upload a quantized BNB 4-bit model

initial commit