metadata
license: apache-2.0
language:
- en
- hi
- gu
- ta
- bn
- mr
tags:
- sumeru
- education
- ncert
- jee
- neet
- india
pipeline_tag: text-generation
Sumeru-rm
A math and science model for Indian students. Covers NCERT Classes 6-12 plus JEE and NEET prep — Physics, Chemistry, Biology, Mathematics.
From Sumeru AI.
Usage
from transformers import AutoModelForCausalLM, AutoProcessor
processor = AutoProcessor.from_pretrained("AgeOfAiTeam/sumeru-rm", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
"AgeOfAiTeam/sumeru-rm", trust_remote_code=True, device_map="auto",
)
messages = [{"role": "user", "content": [{"type": "text",
"text": "Explain Newton's second law of motion."}]}]
text = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = processor(None, text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=300)
print(processor.tokenizer.decode(out[0], skip_special_tokens=True))
Apache 2.0.