Instructions to use Kishan42/Edu_slm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kishan42/Edu_slm with Transformers:

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

pipe = pipeline("text-generation", model="Kishan42/Edu_slm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kishan42/Edu_slm")
model = AutoModelForCausalLM.from_pretrained("Kishan42/Edu_slm", 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 Kishan42/Edu_slm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kishan42/Edu_slm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kishan42/Edu_slm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kishan42/Edu_slm

SGLang

How to use Kishan42/Edu_slm 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 "Kishan42/Edu_slm" \
    --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": "Kishan42/Edu_slm",
		"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 "Kishan42/Edu_slm" \
        --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": "Kishan42/Edu_slm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kishan42/Edu_slm with Docker Model Runner:
```
docker model run hf.co/Kishan42/Edu_slm
```

Edu_slm v1.0

Team Edu_slm domain-specific SLM for JEE Main / JEE Advanced Physics, Chemistry, and Mathematics.

This folder is a merged Hugging Face checkpoint. Load it with:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Edu_slm")
tokenizer = AutoTokenizer.from_pretrained("Edu_slm")

No custom trust_remote_code conversion is required. Architecture is Qwen2ForCausalLM.

Key facts

Base model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Training method: LoRA SFT (r=32, alpha=64), then merge_and_unload
Parameter count: 1,777,088,000
Vocab size: 151,936 (matches config.json)
pad_token: eos_token (<｜end▁of▁sentence｜>, id 151643)
Precision: bfloat16
Chat template: DeepSeek-R1 / Qwen2 (<｜User｜> / <｜Assistant｜><think>)
Training log: train_log.jsonl

Downloads last month: 378

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for Kishan42/Edu_slm

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Finetuned

(658)

this model