Upload README.md with huggingface_hub

README.md

@@ -1,34 +1,45 @@
 ---
 base_model: google/gemma-4-E4B-it
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
   - selenium
   - java
   - experimental
-pipeline_tag: text-generation
 ---
 
 # selenium-java-llm v0.1
 
-> **Experimental. Not an official release.**
+Experimental Gemma 4 E4B fine-tune for Selenium Java test reasoning.
+Not an official release. Not affiliated with SeleniumHQ or Google.
+Hallucinates Selenium APIs — always verify generated code.
+Base model licensing (Gemma Terms of Use) governs use.
+
+## Serve
+
+    vllm serve harsha509/selenium-java-llm-v0.1 --max-model-len 131072
+
+Exposes OpenAI-compatible endpoint at http://localhost:8000/v1.
 
-Gemma 4 E4B fine-tuned to reason about Selenium WebDriver tests in Java —
-diagnosing flaky tests, suggesting resilient locators, explaining failures,
-and emitting `<tool_call>` JSON envelopes.
+## VSCode via Continue.dev
 
-## Disclaimers
+In ~/.continue/config.json add to the "models" array:
 
-- Not affiliated with SeleniumHQ, Google, or any official maintainer.
-- Personal research experiment. No warranty, no support.
-- Hallucinates Selenium APIs. Always verify generated code.
-- Base model licensing (Gemma Terms of Use) governs use.
+    {
+      "title": "selenium-java-llm",
+      "provider": "openai",
+      "model": "harsha509/selenium-java-llm-v0.1",
+      "apiBase": "http://localhost:8000/v1",
+      "apiKey": "not-needed"
+    }
 
-## Usage with vLLM
+## Cursor
 
-```bash
-vllm serve harsha509/selenium-java-llm-v0.1 --max-model-len 32768
-```
+Settings -> Models -> Override OpenAI Base URL:
+- Base URL: http://localhost:8000/v1
+- API Key: any non-empty string
+- Model name: harsha509/selenium-java-llm-v0.1
 
 ## Intended use
 
-Research and experimentation. **Not for** production test triage or unattended code edits.
+Research only. Not for production test triage or unattended code edits.