Update README.md

README.md

@@ -1,3 +1,4 @@
+
 ---
 language:
 - en
@@ -12,7 +13,7 @@ tags:
 - javascript
 - coding-assistant
 - fine-tuning
-- lora
+- merged
 - unsloth
 - gpt-oss
 - vllm
@@ -26,12 +27,13 @@ model-index:
 
 # gpt-oss-coder-v0.1-javascript
 
-A **language-specialized coding model for JavaScript**, fine-tuned from OpenAI’s open-weight **gpt-oss** base with **very small, curated JS data** using **Unsloth**.  
-This release prioritizes **practical code generation quality** over benchmark scores and has been **qualitatively validated** on real prompts (e.g., completions, refactors, docstrings, tests).
+A **language-specialized coding model for JavaScript**, fine-tuned from OpenAI's open-weight **gpt-oss** base with **very small, curated JS data** using **Unsloth**.  
+This release prioritizes **practical code generation quality** over benchmark scores. The model weights have been **merged** and are ready for deployment.
 
-> **Status**: Experimental preview (`v0.1-javascript`).  
-> **Focus**: JS coding tasks (function-level completion, small refactors, idiomatic patterns).  
-> **Why small-data?** Faster iteration and lower cost while proving specialization value.
+> **Status**: Experimental preview (`v0.1-javascript`)  
+> **Focus**: JS coding tasks (function-level completion, small refactors, idiomatic patterns)  
+> **Testing**: Currently undergoing validation with vLLM deployment  
+> **Note**: This repository contains merged weights, not LoRA adapters
 
 ---
 
@@ -39,10 +41,11 @@ This release prioritizes **practical code generation quality** over benchmark sc
 
 - **Model type**: Causal LM (decoder-only), JS-specialized fine-tune  
 - **Base model**: `openai/gpt-oss-20b` (open-weight, Apache-2.0)  
-- **Fine-tuning**: LoRA via **Unsloth**, minimal curated dataset (code snippets, tasks, transformations)  
+- **Fine-tuning**: LoRA via **Unsloth**, weights merged post-training  
 - **License**: Apache-2.0 (derivative weights released under Apache-2.0)  
 - **Author / Maintainer**: `hokar3361`  
 - **Intended Languages**: JavaScript (ES6+); English prompts recommended
+- **Weight Format**: Merged (full model weights)
 
 ---
 
@@ -62,31 +65,81 @@ This release prioritizes **practical code generation quality** over benchmark sc
 
 ## Quickstart
 
+### 1. Start vLLM Server
+
+Since this repository contains **merged weights**, you can run directly with vLLM:
+
 ```bash
 vllm serve hokar3361/gpt-oss-coderjs-v0.1 \
   --async-scheduling \
-  --max-model-len 4096 \
+  --max-model-len 16000 \
   --gpu-memory-utilization 0.90
-For LoRA-only repos, add --lora-modules as per vLLM documentation.
 ```
 
-For merged weights, the above command is sufficient.
+**Recommended**: Use `--max-model-len 16000` for optimal context handling.
+
+### 2. Client Usage (Recommended)
+
+Use the **OpenAI Python client** to call the vLLM server:
+
+```python
+from openai import OpenAI
+
+# Point to your vLLM server
+client = OpenAI(
+    base_url="http://localhost:8000/v1",
+    api_key="dummy"  # vLLM doesn't require auth by default
+)
+
+response = client.completions.create(
+    model="hokar3361/gpt-oss-coderjs-v0.1",
+    prompt="// JavaScript function to validate email addresses\nfunction validateEmail(email) {",
+    # DO NOT specify temperature or max_tokens - let the model use defaults
+)
+
+print(response.choices[0].text)
+```
+
+**Important**: 
+- **Do not specify** `temperature` or `max_tokens` parameters - the model performs best with default values
+- Use the OpenAI Python client for best compatibility and stability
+
+---
+
+## Testing & Validation
+
+### Current Status
+The model is currently being validated using vLLM deployment. Initial testing shows **improved performance** compared to pre-fine-tuning baseline.
+
+### Evaluation Methodology
+- **Test Set**: 50 programming questions from GitHub and Stack Overflow
+- **Judges**: GPT-5 and Claude Opus for response quality assessment
+- **Preliminary Results**: The fine-tuned model demonstrates better code generation quality on JavaScript-specific tasks compared to the base model
+- **Note**: Full benchmark validation is still in progress
+
+---
+
+## Acknowledgements
+
+This work was made possible thanks to the open-weight release of **gpt-oss** by OpenAI, which provided a strong foundation under the Apache-2.0 license.
+
+Special thanks to the open-source community around **Unsloth** for enabling memory-efficient and rapid LoRA fine-tuning on limited hardware.
+
+We also thank the **Hugging Face** and **vLLM** ecosystems for lowering the barrier to experimentation.
+
+---
 
-Acknowledgements
-This work was made possible thanks to the open-weight release of gpt-oss by OpenAI, which provided a strong foundation under the Apache-2.0 license.
-Special thanks to the open-source community around Unsloth for enabling memory-efficient and rapid LoRA fine-tuning on limited hardware.
-We also thank the Hugging Face and vLLM ecosystems for lowering the barrier to experimentation.
+## Disclaimer & Experimental Status
 
-Disclaimer & Experimental Status
-This model (v0.1-javascript) is highly experimental:
+This model (`v0.1-javascript`) is highly experimental:
 
-Small data: Fine-tuned on a very small JavaScript-focused dataset, mainly to validate the workflow and feasibility of language specialization.
+- **Small data**: Fine-tuned on a very small JavaScript-focused dataset, mainly to validate the workflow and feasibility of language specialization.
 
-Not production-ready: The model may generate incomplete, insecure, or non-idiomatic code; do not rely on it for production use without careful review.
+- **Not production-ready**: The model may generate incomplete, insecure, or non-idiomatic code; do not rely on it for production use without careful review.
 
-Benchmarks not representative: Due to issues in the current verification scripts, benchmark scores are not included. Assessment is based only on qualitative inspection of outputs, which show promising improvements but remain anecdotal.
+- **Testing in progress**: While initial results from GPT-5 and Opus evaluation show improvements, comprehensive benchmarking is ongoing.
 
-Early stage: This is only an initial exploration; future versions with larger, more diverse training corpora are expected to improve stability and coverage.
+- **Early stage**: This is only an initial exploration; future versions with larger, more diverse training corpora are expected to improve stability and coverage.
 
-We share this release to contribute to the community and gather early feedback.
-Use responsibly, validate outputs, and treat this as a proof-of-concept.
+We share this release to contribute to the community and gather early feedback.  
+**Use responsibly, validate outputs, and treat this as a proof-of-concept.**