Instructions to use kuotient/EEVE-Instruct-Math-10.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kuotient/EEVE-Instruct-Math-10.8B with Transformers:

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

pipe = pipeline("text-generation", model="kuotient/EEVE-Instruct-Math-10.8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kuotient/EEVE-Instruct-Math-10.8B")
model = AutoModelForCausalLM.from_pretrained("kuotient/EEVE-Instruct-Math-10.8B")
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 kuotient/EEVE-Instruct-Math-10.8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kuotient/EEVE-Instruct-Math-10.8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kuotient/EEVE-Instruct-Math-10.8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kuotient/EEVE-Instruct-Math-10.8B

SGLang

How to use kuotient/EEVE-Instruct-Math-10.8B 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 "kuotient/EEVE-Instruct-Math-10.8B" \
    --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": "kuotient/EEVE-Instruct-Math-10.8B",
		"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 "kuotient/EEVE-Instruct-Math-10.8B" \
        --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": "kuotient/EEVE-Instruct-Math-10.8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kuotient/EEVE-Instruct-Math-10.8B with Docker Model Runner:
```
docker model run hf.co/kuotient/EEVE-Instruct-Math-10.8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

EEVE-Instruct-Math-10.8B

EEVE-Math 프로젝트는

Orca-Math-200k 번역 (Orca-Math: Unlocking the potential of SLMs in Grade School Math)
gsm8k 번역, lm_eval 활용
Mergekit을 이용한 dare-ties 사용 (DARE)

에 대한 내용을 포괄하고 있습니다.

이 모델은 EEVE-Math와 EEVE-Instruct의 dare-ties로 병합한 병합 모델입니다. 이 프로젝트는 이런 과정을 통해 특화 모델의 EEVE-Math의 성능을 많이 잃지 않고 Instruct 모델의 사용성을 유지할 수 있음을 보여주는 Proof of concept의 성격을 가지고 있습니다.

Model	gsm8k-ko(pass@1)
EEVE(Base)	0.4049
EEVE-Math (epoch 1)	0.508
EEVE-Math (epoch 2)	0.539
EEVE-Instruct	0.4511
EEVE-Instruct + Math	0.4845

Merge Details

This model was merged using the DARE TIES merge method using yanolja/EEVE-Korean-Instruct-10.8B-v1.0 as a base.

Models Merged

The following models were included in the merge:

kuotient/EEVE-Math-10.8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: yanolja/EEVE-Korean-10.8B-v1.0
    # no parameters necessary for base model
  - model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
    parameters:
      density: 0.53
      weight: 0.6
  - model: kuotient/EEVE-Math-10.8B
    parameters:
      density: 0.53
      weight: 0.4
merge_method: dare_ties
base_model: yanolja/EEVE-Korean-10.8B-v1.0
parameters:
  int8_mask: true
dtype: bfloat16

Evaluation

gsm8k-ko, kobest

git clone https://github.com/kuotient/lm-evaluation-harness.git
cd lm-evaluation-harness
pip install -e .

lm_eval --model hf \
    --model_args pretrained=yanolja/EEVE-Korean-Instruct-2.8B-v1.0 \
    --tasks gsm8k-ko \
    --device cuda:0 \
    --batch_size auto:4

Model	gsm8k(pass@1)	boolq(acc)	copa(acc)	hellaswag(acc)	Overall
yanolja/EEVE-Korean-10.8B-v1.0	0.4049	-	-	-	-
yanolja/EEVE-Korean-Instruct-10.8B-v1.0	0.4511	0.8668	0.7450	0.4940	0.6392
EEVE-Math-10.8B	0.5390	0.8027	0.7260	0.4760	0.6359
EEVE-Instruct-Math-10.8B	0.4845	0.8519	0.7410	0.4980	0.6439