Instructions to use AdarshSingh7647/Eklav-9B-Math-CotGen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdarshSingh7647/Eklav-9B-Math-CotGen with Transformers:

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

pipe = pipeline("text-generation", model="AdarshSingh7647/Eklav-9B-Math-CotGen")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AdarshSingh7647/Eklav-9B-Math-CotGen")
model = AutoModelForCausalLM.from_pretrained("AdarshSingh7647/Eklav-9B-Math-CotGen", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AdarshSingh7647/Eklav-9B-Math-CotGen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdarshSingh7647/Eklav-9B-Math-CotGen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdarshSingh7647/Eklav-9B-Math-CotGen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AdarshSingh7647/Eklav-9B-Math-CotGen

SGLang

How to use AdarshSingh7647/Eklav-9B-Math-CotGen 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 "AdarshSingh7647/Eklav-9B-Math-CotGen" \
    --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": "AdarshSingh7647/Eklav-9B-Math-CotGen",
		"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 "AdarshSingh7647/Eklav-9B-Math-CotGen" \
        --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": "AdarshSingh7647/Eklav-9B-Math-CotGen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AdarshSingh7647/Eklav-9B-Math-CotGen with Docker Model Runner:
```
docker model run hf.co/AdarshSingh7647/Eklav-9B-Math-CotGen
```

Eklav-9B-Math-CotGen (CotGen baseline)

Eklav trains a model to pick up a teacher's reasoning mid thought rather than imitate it end to end. The student sees a partial reasoning trace from the teacher, with the answer revealing tail removed, and learns to continue reasoning and produce the answer on its own. The model's own reasoning is conditioned on the teacher's partial trace during training rather than trained to reproduce it word for word. Same base model, same training data as standard full trace CoT distillation, only the training objective changes.

Highlights

Standard full trace CoT SFT baseline used to measure Eklav's improvement at this scale

Model details


Base model	zai-org/GLM-Z1-9B-0414
Task	Math reasoning
Training method	CotGen (standard full trace CoT SFT, baseline)
Format	Merged bf16 checkpoint

Results

Pass@1 (%), single evaluation run per benchmark.

Benchmark	AIME 2025	AIME 1983-2024	GPQA-Diamond	GSM8K	MATH-500	Omni-MATH	MMLU
CotGen	35.2	59.3	49.8	95.5	91.2	39.8	81.0

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "AdarshSingh7647/Eklav-9B-Math-CotGen"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")