Unsloth Model Card

README.md

@@ -1,40 +1,21 @@
 ---
-base_model: google/gemma-3n-e4b-it
-library_name: peft
-license: apache-2.0
+base_model: harsha509/selenium-java-llm-v0.1
 tags:
-  - lora
-  - selenium
-  - java
-  - experimental
-pipeline_tag: text-generation
+- text-generation-inference
+- transformers
+- unsloth
+- gemma4
+license: apache-2.0
+language:
+- en
 ---
 
-# selenium-java-llm v0.1
-
-> **Experimental. Not an official release.**
-
-A LoRA adapter on **Gemma 3n E4B** that tries to reason about Selenium
-WebDriver tests in Java — diagnosing flaky tests, suggesting resilient
-locators, explaining failures, and emitting `<tool_call>` JSON envelopes.
-
-## Disclaimers
-
-- 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 combined use.
-
-## Usage with vLLM
+# Uploaded finetuned  model
 
-```bash
-vllm serve google/gemma-3n-e4b-it \
-    --enable-lora \
-    --lora-modules selenium-java-llm=harsha509/selenium-java-llm-v0.1 \
-    --max-lora-rank 32 \
-    --max-model-len 4096
-```
+- **Developed by:** harsha509
+- **License:** apache-2.0
+- **Finetuned from model :** harsha509/selenium-java-llm-v0.1
 
-## Intended use
+This gemma4 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-Research and experimentation. **Not for** production test triage or unattended code edits.
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)