Instructions to use blockblockblock/Mengzi3-13B-Base-bpw4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blockblockblock/Mengzi3-13B-Base-bpw4 with Transformers:

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

pipe = pipeline("text-generation", model="blockblockblock/Mengzi3-13B-Base-bpw4")

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

tokenizer = AutoTokenizer.from_pretrained("blockblockblock/Mengzi3-13B-Base-bpw4")
model = AutoModelForCausalLM.from_pretrained("blockblockblock/Mengzi3-13B-Base-bpw4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use blockblockblock/Mengzi3-13B-Base-bpw4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blockblockblock/Mengzi3-13B-Base-bpw4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Mengzi3-13B-Base-bpw4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/blockblockblock/Mengzi3-13B-Base-bpw4

SGLang

How to use blockblockblock/Mengzi3-13B-Base-bpw4 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 "blockblockblock/Mengzi3-13B-Base-bpw4" \
    --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": "blockblockblock/Mengzi3-13B-Base-bpw4",
		"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 "blockblockblock/Mengzi3-13B-Base-bpw4" \
        --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": "blockblockblock/Mengzi3-13B-Base-bpw4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use blockblockblock/Mengzi3-13B-Base-bpw4 with Docker Model Runner:
```
docker model run hf.co/blockblockblock/Mengzi3-13B-Base-bpw4
```

Mengzi3-13B-Base-bpw4 / tokenizer.model

blockblockblock

Upload folder using huggingface_hub

6500a24 verified over 2 years ago

History Blame Contribute Delete

1.47 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: dc35e563674487b3ea7e700798b5ade63cc69ab590255c78d039dd178ba9ef12
Size of remote file:: 1.47 MB
SHA256:: d6b1aa0f182753a759de96a7bd6e763659fd6f06dbdabc83356b9cbd71da6f41

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.