Instructions to use shivs28/jee_nujan_mix_v2_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shivs28/jee_nujan_mix_v2_base with Transformers:

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

pipe = pipeline("text-generation", model="shivs28/jee_nujan_mix_v2_base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shivs28/jee_nujan_mix_v2_base")
model = AutoModelForCausalLM.from_pretrained("shivs28/jee_nujan_mix_v2_base")
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

vLLM

How to use shivs28/jee_nujan_mix_v2_base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shivs28/jee_nujan_mix_v2_base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shivs28/jee_nujan_mix_v2_base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shivs28/jee_nujan_mix_v2_base

SGLang

How to use shivs28/jee_nujan_mix_v2_base 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 "shivs28/jee_nujan_mix_v2_base" \
    --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": "shivs28/jee_nujan_mix_v2_base",
		"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 "shivs28/jee_nujan_mix_v2_base" \
        --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": "shivs28/jee_nujan_mix_v2_base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shivs28/jee_nujan_mix_v2_base with Docker Model Runner:
```
docker model run hf.co/shivs28/jee_nujan_mix_v2_base
```

JEE NUJAN MIX V2 - Base Merged Model

Model Description

This is the base merged model for JEE mathematics problem solving, created by combining three specialized models using linear interpolation. This model serves as the foundation for further fine-tuning on mathematical datasets.

Model Architecture

Merged Models:

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B (40% weight) - Advanced reasoning capabilities
Qwen/Qwen2.5-Math-1.5B (35% weight) - Mathematical problem solving
microsoft/phi-2 (25% weight) - General reasoning and language understanding

Merge Method: Linear interpolation with weight normalization Output Format: Float16 for efficiency Tokenizer: Based on DeepSeek-R1-Distill-Qwen-1.5B

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load the merged base model
tokenizer = AutoTokenizer.from_pretrained("shivs28/jee_nujan_mix_v2_base")
model = AutoModelForCausalLM.from_pretrained(
    "shivs28/jee_nujan_mix_v2_base", 
    torch_dtype=torch.float16,
    device_map="auto"
)

# Use for mathematical reasoning
prompt = "Solve: What is the derivative of x^2 + 3x + 1?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Intended Use

This base model is intended to be:

Fine-tuned on specific mathematical datasets for enhanced performance
Used as starting point for educational AI applications
Evaluated for mathematical reasoning capabilities

Next Steps

This base model will be fine-tuned on comprehensive mathematical datasets including:

Competition Mathematics (MATH dataset)
GSM8K word problems
MathQA reasoning problems
AQuA-RAT algebraic problems
Custom JEE advanced problems

Model Card Authors

Created by the JEE NUJAN MIX team for educational purposes.

Citation

Please cite the original base models:

DeepSeek-R1-Distill-Qwen-1.5B
Qwen2.5-Math-1.5B
Phi-2 tags:
- open-llm-leaderboard
- math
- gsm8k
- casual-lm
- fine-tuned

This model is part of the NUJAN educational initiative.

Downloads last month: 1

Safetensors

Model size

2B params

Tensor type

F32

Model tree for shivs28/jee_nujan_mix_v2_base

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Math-1.5B

Finetuned

(189)

this model