Instructions to use Harsh2026verma/code-generator-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Harsh2026verma/code-generator-model with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Harsh2026verma/code-generator-model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Harsh2026verma/code-generator-model")
model = AutoModelForCausalLM.from_pretrained("Harsh2026verma/code-generator-model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Harsh2026verma/code-generator-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harsh2026verma/code-generator-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harsh2026verma/code-generator-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Harsh2026verma/code-generator-model

SGLang

How to use Harsh2026verma/code-generator-model with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Harsh2026verma/code-generator-model" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harsh2026verma/code-generator-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Harsh2026verma/code-generator-model" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harsh2026verma/code-generator-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Harsh2026verma/code-generator-model with Docker Model Runner:
```
docker model run hf.co/Harsh2026verma/code-generator-model
```

code-generator-model / README.md

Harsh2026verma

Update README.md

abd0547 verified about 1 month ago

preview code

raw

history blame contribute delete

2.14 kB

	---
	library_name: transformers
	license: mit
	metrics:
	- accuracy
	- bleu
	- code_eval
	pipeline_tag: text-generation
	tags:
	- cybersecurity
	- web-development
	- multilingual
	- hindi
	- hinglish
	- code-generation
	- security
	- ddos-protection
	- sql-injection
	- xss-prevention
	---

	# 🔒 Hinglish Cybersecurity & Web Development Expert

	## Model Overview

	HinglishCyberSec is a fine-tuned CodeLlama-7B model specialized in multilingual cybersecurity and full-stack web development. It understands and generates code in Hindi, English, and Hinglish (Hindi+English mix).

	### 🎯 What This Model Does

	\| Capability \| Description \|
	\|------------\|-------------\|
	\| 🌐 Multilingual \| Responds in Hindi, English, or Hinglish \|
	\| 🛡️ Cybersecurity \| SQL injection, XSS, DDoS, JWT, Encryption, CSRF protection \|
	\| 💻 Web Development \| HTML, CSS, JavaScript, React, Flask, Express, PHP \|
	\| 🔒 Security Headers \| CSP, HSTS, X-Frame-Options implementation \|
	\| 📊 Rate Limiting \| DDoS protection, API rate limiting \|
	\| 🔐 Authentication \| JWT, bcrypt, session management \|
	\| 📝 Code Explanation \| Explains code in simple Hinglish \|

	---

	## Model Details

	### Basic Information

	- Developed by: Harsh Verma
	- Model type: Causal Language Model (Fine-tuned CodeLlama-7B)
	- Language(s): Hindi, English, Hinglish (Hindi + English mix)
	- License: MIT
	- Base Model: CodeLlama-7B
	- Fine-tuned on: Custom multilingual cybersecurity + web development dataset

	### Model Sources

	- Repository: [Your ]
	- Demo: [https://huggingface.co/spaces/Harsh2026verma/Rudra-chatbot]
	- Dataset: [Link to your dataset]

	---

	## Uses

	### Direct Use

	This model can be used for:

	```python
	# 1. Generate secure code in Hinglish
	response = model.generate("SQL injection se bachne ka tarika batao")

	# 2. Create web applications
	response = model.generate("Ek responsive navbar banao with logo and 3 links")

	# 3. Security audit
	response = model.generate("Is code mein SQL injection vulnerability hai?")

	# 4. DDoS protection
	response = model.generate("Flask mein rate limiting kaise lagayein?")