Update model card for v0.8

README.md

@@ -1,3 +1,4 @@
+
 ---
 base_model: unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit
 tags:
@@ -19,25 +20,25 @@ Pre-fine-tuned LoRA adapters for unsloth/Qwen2.5-Coder-32B-Instruct.
 - https://huggingface.co/datasets/Jake5/wmx-doc-user
 - https://huggingface.co/datasets/Jake5/wmx-doc-robot
 
-## Version v0.7
+## Version v0.8
 - Source: lora_model
 - Base model: unsloth/Qwen2.5-Coder-32B-Instruct
-- Uploaded on: 2025-09-10
+- Uploaded on: 2025-09-11
 
 ## 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_v0.7")
-tokenizer = AutoTokenizer.from_pretrained("Jake5/Qwen2.5-Coder-32B-Instruct-WMX", subfolder="adapters_v0.7")
+model = PeftModel.from_pretrained(base_model, "Jake5/Qwen2.5-Coder-32B-Instruct-WMX", subfolder="adapters_v0.8")
+tokenizer = AutoTokenizer.from_pretrained("Jake5/Qwen2.5-Coder-32B-Instruct-WMX", subfolder="adapters_v0.8")
 ```
 
 ## 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_v0.7 \
+    --lora-modules my-lora=Jake5/Qwen2.5-Coder-32B-Instruct-WMX/adapters_v0.8 \
     --dtype bfloat16 \
     --port 8000
 ```