Instructions to use Jagneshdeveloper/Prakrit1.0-7b-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jagneshdeveloper/Prakrit1.0-7b-small with Transformers:

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

pipe = pipeline("text-generation", model="Jagneshdeveloper/Prakrit1.0-7b-small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jagneshdeveloper/Prakrit1.0-7b-small")
model = AutoModelForCausalLM.from_pretrained("Jagneshdeveloper/Prakrit1.0-7b-small", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jagneshdeveloper/Prakrit1.0-7b-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jagneshdeveloper/Prakrit1.0-7b-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jagneshdeveloper/Prakrit1.0-7b-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jagneshdeveloper/Prakrit1.0-7b-small

SGLang

How to use Jagneshdeveloper/Prakrit1.0-7b-small 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 "Jagneshdeveloper/Prakrit1.0-7b-small" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jagneshdeveloper/Prakrit1.0-7b-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Jagneshdeveloper/Prakrit1.0-7b-small" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jagneshdeveloper/Prakrit1.0-7b-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jagneshdeveloper/Prakrit1.0-7b-small with Docker Model Runner:
```
docker model run hf.co/Jagneshdeveloper/Prakrit1.0-7b-small
```

Prakrit1.0-7b-small / README.md

Jagneshdeveloper

Update README.md

1c87483 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

3.28 kB

	---
	license: apache-2.0
	tags:
	- text-generation-inference
	- transformers
	- code
	- agent
	- text-generation
	- custom-tune
	base_model:
	- Qwen/Qwen2.5-7B
	language:
	- en
	pipeline_tag: text-generation
	---

	<div align="center">

	# 🇮🇳 Prakrit1.0-7B-Small

	## 🌟 Made in India 🌟

	<h3>🚀 A High-Performance Specialist Model</h3>

	<p align="center">
	Developed by <b>Jagneshdeveloper</b>
	</p>

	---

	`📄 License: Apache 2.0` \| `⚙️ Parameters: 7 Billion` \| `💻 Focus: Coding & Agents`

	</div>

	---

	## 📌 Overview

	Prakrit1.0-7B-Small is an advanced 7-billion parameter large language model proudly developed by Jagneshdeveloper. Built on top of the powerful Qwen2.5 architecture, this model has been custom-engineered and fine-tuned specifically for autonomous agentic workflows and elite coding tasks.

	By optimizing the baseline capabilities, Prakrit1.0-7B-Small delivers rapid, highly accurate code synthesis and structured logical reasoning.

	---

	## ⚡ Key Capabilities

	* 💻 Coding Specialist: Optimized to write, debug, explain, and refactor complex code across multiple programming languages (Python, JavaScript, C++, Go, etc.).
	* 🤖 Agentic Excellence: Engineered with a strong grasp of tool-use planning, step-by-step reasoning, and generating strictly formatted outputs (like JSON or system commands).
	* 🌐 Multitask Efficiency: Maintains top-tier performance in standard text generation, summarisation, and translation tasks.

	---

	## 📊 Model Summary

	* Model Name: Prakrit1.0-7B-Small
	* Developer: Jagneshdeveloper
	* Base Architecture: Built on top of Qwen2.5
	* Parameters: 7 Billion (7B)
	* License: Apache 2.0
	* Primary Language: English (en)

	---

	## 💻 Quick Start

	You can quickly load and deploy Prakrit1.0-7B-Small using the Hugging Face `transformers` library:

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	model_name = "Jagneshdeveloper/prakrit1.0-7b-small"

	# Load the optimized tokenizer and model
	tokenizer = AutoTokenizer.from_pretrained(model_name)
	model = AutoModelForCausalLM.from_pretrained(
	model_name,
	device_map="auto",
	torch_dtype=torch.bfloat16
	)

	# Test prompt for coding/agentic workflow
	prompt = "Write a Python script to scrape website data and format it into a structured JSON array."
	inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
	outputs = model.generate(**inputs, max_new_tokens=300, temperature=0.3)

	print(tokenizer.decode(outputs, skip_special_tokens=True))
	```

	---

	## 🛠️ Intended Uses & Limitations

	### Ideal Use Cases
	* Building autonomous AI agents and execution loops.
	* Serving as an on-device or cloud-hosted programming assistant.
	* Handling complex data extraction and formatting.

	### Limitations
	* As a 7B model, users should verify complex logic or math outputs before deploying code directly into production environments.
	* Performance on highly specialized regional tasks may vary based on your prompt structures.

	---

	## 🤝 Attribution & Support

	Created with ❤️ by Jagneshdeveloper in India. This model is distributed under the Apache 2.0 license. For feedback, feature requests, or collaborations, feel free to open a discussion in the community tab!