Instructions to use HUNGTZE/T1plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HUNGTZE/T1plus with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/mnt/moe_ub/checkpoints/GLM-4.6V")
model = PeftModel.from_pretrained(base_model, "HUNGTZE/T1plus")

Transformers

How to use HUNGTZE/T1plus with Transformers:

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

pipe = pipeline("text-generation", model="HUNGTZE/T1plus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("HUNGTZE/T1plus", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HUNGTZE/T1plus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HUNGTZE/T1plus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HUNGTZE/T1plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HUNGTZE/T1plus

SGLang

How to use HUNGTZE/T1plus 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 "HUNGTZE/T1plus" \
    --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": "HUNGTZE/T1plus",
		"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 "HUNGTZE/T1plus" \
        --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": "HUNGTZE/T1plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HUNGTZE/T1plus with Docker Model Runner:
```
docker model run hf.co/HUNGTZE/T1plus
```

GLM-4.6V SFT LoRA (T1plus)

Fine-tuned LoRA adapter for GLM-4.6V 108B MoE Vision-Language Model.

Model Details

Base Model: GLM-4.6V 108B MoE (128 experts, 8 active)
Training Method: SFT with LoRA
LoRA Rank: 64
LoRA Alpha: 128
Training Epochs: 2
Learning Rate: 2e-05
Max Sequence Length: 4096

Training Configuration

Batch Size: 1
Gradient Accumulation: 8
Precision: bfloat16

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "THUDM/GLM-4.6V",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "HUNGTZE/T1plus")

Framework Versions

PEFT 0.18.0
Transformers 4.x

Downloads last month: -