Fix incorrect weight-format references (#3872)

There is no such param as weight_format, this is the only parameter ovms
uses which has - instead of _

Author: dkalinowski

demos/continuous_batching/agentic_ai/README.md

@@ -105,7 +105,7 @@ curl -L -o models/openai/gpt-oss-20b/chat_template.jinja https://raw.githubuserc
 :::
 ::::
 
-> **Note:** To use these models on NPU, set `--weight_format` to either **int4** or **nf4**. When specifying `--extra_quantization_params`, ensure that `ratio` is set to **1.0** and `group_size` is set to **-1** or **128**. For more details, see [OpenVINO GenAI on NPU](https://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-genai/inference-with-genai-on-npu.html).
+> **Note:** To use these models on NPU, set `--weight-format` to either **int4** or **nf4**. When specifying `--extra_quantization_params`, ensure that `ratio` is set to **1.0** and `group_size` is set to **-1** or **128**. For more details, see [OpenVINO GenAI on NPU](https://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-genai/inference-with-genai-on-npu.html).
 
 ### Direct pulling of pre-configured HuggingFace models from docker containers
 
@@ -242,7 +242,7 @@ ovms.exe --rest_port 8000 --source_model Qwen/Qwen3-Coder-30B-A3B-Instruct --mod
 :::{tab-item} gpt-oss-20b
 :sync: gpt-oss-20b
 ```bat
-ovms.exe --rest_port 8000 --source_model openai/gpt-oss-20b --model_repository_path models --tool_parser gptoss --reasoning_parser gptoss --target_device GPU --task text_generation --pipeline_type LM --weight_format int4
+ovms.exe --rest_port 8000 --source_model openai/gpt-oss-20b --model_repository_path models --tool_parser gptoss --reasoning_parser gptoss --target_device GPU --task text_generation --pipeline_type LM --weight-format int4
 ```
 > **Note:**: Use `--pipeline_type LM` for export and `--target device GPU` for deployment. Expect continuous batching and CPU support in weekly or 2026.0+ releases.
 :::
@@ -475,7 +475,7 @@ docker run -d --user $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/model
 ```bash
 docker run -d --user $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/models --device /dev/dri --group-add=$(stat -c "%g" /dev/dri/render* | head -n 1) openvino/model_server:weekly \
 --rest_port 8000 --source_model openai/gpt-oss-20b --model_repository_path models \
---tool_parser gptoss --reasoning_parser gptoss --target_device GPU --task text_generation --enable_prefix_caching true --pipeline_type LM --weight_format int4
+--tool_parser gptoss --reasoning_parser gptoss --target_device GPU --task text_generation --enable_prefix_caching true --pipeline_type LM --weight-format int4
 ```
 > **Note:**: Use `--pipeline_type LM` for export and `--target device GPU` for deployment. Expect continuous batching and CPU support in weekly or 2026.0+ releases.
 :::