Qwen3 Vl 32b Soccer v11 LoRA

--- license: other license_name: tongyi-qianwen-license license_link: https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct/blob/main/LICENSE base_model: Qwen/Qwen3-VL-32B-Instruct-FP8 tags: - soccer - video-classification - event-detection - lora - peft - qwen3-vl language: - en pipeline_tag: video-text-to-text --- # qwen3-vl-32b-soccer-v11-lora LoRA adapter (checkpoint-150, the production pick) for the soccer event classifier. ~2.27 GB. Use this if you want to: - Apply the adapter on top of a different base (e.g., the bf16 Qwen3-VL-32B rather than the FP8 quant) - Continue training from this checkpoint - Inspect the LoRA weights **For inference, most users will want the merged FP8 model instead:** [acatorcini/qwen3-vl-32b-soccer-v11-fp8](https://huggingface.co/acatorcini/qwen3-vl-32b-soccer-v11-fp8). That single artifact loads directly into vLLM with no merge step. ## Adapter config ``` peft_type: LORA r: 64 lora_alpha: 128 lora_dropout: 0.05 target_modules: [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj] base_model_name_or_path: (an internal v8-32b BF16 merge — see below) ``` > **Base-model note**: The adapter's `adapter_config.json` references an > internal predecessor checkpoint (`v8-32b/merged-bf16-c300`) as its base. > The merged FP8 production model was built by applying THIS adapter to > THAT predecessor base and then quantizing. To reproduce the merge against > the public Qwen3-VL-32B base, expect slight numerical differences. ## Use with PEFT ```python from transformers import AutoModelForCausalLM from peft import PeftModel base = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-VL-32B-Instruct", torch_dtype="auto", device_map="auto", ) model = PeftModel.from_pretrained(base, "acatorcini/qwen3-vl-32b-soccer-v11-lora") ``` ## Training data + intended use Same as the merged model — see [acatorcini/qwen3-vl-32b-soccer-v11-fp8](https://huggingface.co/acatorcini/qwen3-vl-32b-soccer-v11-fp8). ## License Inherits the Qwen3-VL [Tongyi Qianwen License](https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct/blob/main/LICENSE). ## Related - Merged FP8 (recommended for inference): [acatorcini/qwen3-vl-32b-soccer-v11-fp8](https://huggingface.co/acatorcini/qwen3-vl-32b-soccer-v11-fp8) - Pipeline source: [github.com/acato/soccer-video-pipeline](https://github.com/acato/soccer-video-pipeline)

Source context: 9 downloads · 0 likes · Pipeline video-text-to-text · Library peft · Repo acatorcini/qwen3-vl-32b-soccer-v11-lora

Source context: 5 downloads · 0 likes · Pipeline video-text-to-text · Library peft · Repo acatorcini/qwen3-vl-32b-soccer-v11-lora