Instructions to use HUNGTZE/glm4v-sft-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HUNGTZE/glm4v-sft-lora 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/glm4v-sft-lora")

Transformers

How to use HUNGTZE/glm4v-sft-lora with Transformers:

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

pipe = pipeline("text-generation", model="HUNGTZE/glm4v-sft-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("HUNGTZE/glm4v-sft-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HUNGTZE/glm4v-sft-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HUNGTZE/glm4v-sft-lora"
# 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/glm4v-sft-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HUNGTZE/glm4v-sft-lora

SGLang

How to use HUNGTZE/glm4v-sft-lora 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/glm4v-sft-lora" \
    --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/glm4v-sft-lora",
		"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/glm4v-sft-lora" \
        --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/glm4v-sft-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HUNGTZE/glm4v-sft-lora with Docker Model Runner:
```
docker model run hf.co/HUNGTZE/glm4v-sft-lora
```

GLM-4.6V SFT LoRA

這是基於 GLM-4.6V 108B MoE 模型進行 SFT (Supervised Fine-Tuning) 訓練的 LoRA adapter。

模型資訊

Base Model: GLM-4.6V 108B MoE (128 experts, 8 active)
Training Method: QLoRA (4-bit quantization + LoRA)
LoRA Rank: 64
LoRA Alpha: 128
Training Steps: 600
Max Sequence Length: 4096

訓練配置

Hardware: 4x NVIDIA H100 80GB
Precision: BF16
Optimizer: AdamW
Learning Rate: 2e-5
Batch Size: 1 per GPU
Gradient Accumulation: 8

使用方式

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# 載入基礎模型
base_model = AutoModelForCausalLM.from_pretrained(
    "your-base-model-path",
    device_map="auto",
    torch_dtype=torch.bfloat16
)

# 載入 LoRA adapter
model = PeftModel.from_pretrained(base_model, "HUNGTZE/glm4v-sft-lora")

# 載入 tokenizer
tokenizer = AutoTokenizer.from_pretrained("HUNGTZE/glm4v-sft-lora")

Framework Versions

PEFT: 0.18.0
Transformers: 4.x
PyTorch: 2.x

Downloads last month: 1