Instructions to use Heng666/EastAsia-4x7B-Moe-experiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heng666/EastAsia-4x7B-Moe-experiment with Transformers:

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

pipe = pipeline("text-generation", model="Heng666/EastAsia-4x7B-Moe-experiment")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Heng666/EastAsia-4x7B-Moe-experiment")
model = AutoModelForCausalLM.from_pretrained("Heng666/EastAsia-4x7B-Moe-experiment", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Heng666/EastAsia-4x7B-Moe-experiment with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Heng666/EastAsia-4x7B-Moe-experiment"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heng666/EastAsia-4x7B-Moe-experiment",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Heng666/EastAsia-4x7B-Moe-experiment

SGLang

How to use Heng666/EastAsia-4x7B-Moe-experiment 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 "Heng666/EastAsia-4x7B-Moe-experiment" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heng666/EastAsia-4x7B-Moe-experiment",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Heng666/EastAsia-4x7B-Moe-experiment" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Heng666/EastAsia-4x7B-Moe-experiment",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Heng666/EastAsia-4x7B-Moe-experiment with Docker Model Runner:
```
docker model run hf.co/Heng666/EastAsia-4x7B-Moe-experiment
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

EastAsia-4x7B-Moe-experiment

EastAsia-4x7B-Moe-experiment is a Mixure of Experts (MoE) made with the following models using LazyMergekit:

🧩 Configuration

gate_mode: hidden
dtype: bfloat16
base_model: mlabonne/Marcoro14-7B-slerp
experts:
  - source_model: MediaTek-Research/Breeze-7B-Instruct-v0.1
    positive_prompts:
    - "翻譯"
  - source_model: augmxnt/shisa-7b-v1
    positive_prompts:
    - "翻訳"
  - source_model: beomi/OPEN-SOLAR-KO-10.7B
    positive_prompts:
    - "번역"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Heng666/EastAsia-4x7B-Moe-experiment"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	42.12
AI2 Reasoning Challenge (25-Shot)	39.51
HellaSwag (10-Shot)	48.92
MMLU (5-Shot)	56.20
TruthfulQA (0-shot)	49.83
Winogrande (5-shot)	58.09
GSM8k (5-shot)	0.15

Downloads last month: 51

Safetensors

Model size

19B params

Tensor type

BF16

Model tree for Heng666/EastAsia-4x7B-Moe-experiment

Quantizations

3 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

39.510
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

48.920
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

56.200
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

49.830
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

58.090
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.150