Update model card for v0.4

README.md

@@ -1,5 +1,31 @@
----
-license: apache-2.0
-tags:
-- unsloth
----
+
+# Qwen2.5-Coder-32B-Instruct-WMX
+Pre-fine-tuned LoRA adapters for unsloth/Qwen2.5-Coder-32B-Instruct.
+
+**This lora adapters have been fine-tuned for WMX services using the folowing datasets.**
+- https://huggingface.co/datasets/Jake5/movensys-info
+- https://huggingface.co/datasets/Jake5/wmx-doc-user
+- https://huggingface.co/datasets/Jake5/wmx-doc-robot
+
+## Version v0.4
+- Source: lora_model
+- Base model: unsloth/Qwen2.5-Coder-32B-Instruct
+- Uploaded on: 2025-09-05
+
+## Usage
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-Coder-32B-Instruct")
+model = PeftModel.from_pretrained(base_model, "Jake5/Qwen2.5-Coder-32B-Instruct-WMX", subfolder="adapters_v0.4")
+tokenizer = AutoTokenizer.from_pretrained("Jake5/Qwen2.5-Coder-32B-Instruct-WMX", subfolder="adapters_v0.4")
+```
+
+## vLLM Serving
+```bash
+python -m vllm.entrypoints.openai.api_server \
+    --model unsloth/Qwen2.5-Coder-32B-Instruct \
+    --lora-modules my-lora=Jake5/Qwen2.5-Coder-32B-Instruct-WMX/adapters_v0.4 \
+    --dtype bfloat16 \
+    --port 8000
+```