Instructions to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with Transformers:

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

pipe = pipeline("image-text-to-text", model="lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated")
model = AutoModelForMultimodalLM.from_pretrained("lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated

SGLang

How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated 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 "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated" \
    --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": "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated" \
        --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": "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with Docker Model Runner:
```
docker model run hf.co/lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated
```

GLM-5.3-Flash-tr3-4bpw-Abliterated / results /tp2-runtime-window-kld.json

lovesenko

Add files using upload-large-folder tool

ca44eaa verified 2 days ago

Raw

History Blame Contribute Delete

1.48 kB

{"compute_device":"cuda:0","compute_dtype":"float64","elapsed_seconds":1.5412861499935389,"kld_direction":"bf16_teacher_to_custom_tp2_runtime","max_mean_kld":0.06,"mean_kld_gate_passed":true,"metric":"tokenwise KL over the sealed qualification window","prediction_positions":2047,"report_sha256":"2cfd1b90a65162784de5b67e1b05ef7a15f98979b77156092d5f7500c607ba67","runtime_logits_sha256":"280c12452f429a79724cd1715a5bed2462de98a547746a80f04e7b8cdcd34746","runtime_rank_output_identical":true,"runtime_raw_decoded_parity_passed":false,"runtime_receipt_sha256":"cbd13544b47f7a0fa9df62af43da94e30ad107c6ebac5eea40443a2a485e3d3a","schema":"quant-pipeline.glm53-custom-tp2-runtime-window-kld.v1","summary":{"count":2047,"cvar95":0.18272796855202927,"max":1.018581137984496,"mean":0.022750847877671544,"p50":0.00993991401651846,"p95":0.07140553100728228,"p99":0.22317846601861877,"std":0.05681743679919093},"teacher_logits_sha256":"9f49af1b1b1a6ac88a00f5feaa89c25232597306d73d7c0cd30bb7e9c775cfb6","teacher_receipt_sha256":"2ae08117c3d4247f747b2a9a889b68e1a06387b788d56a0bf23bb950c77bc5a5","token_ids_sha256":"338027e62f41540f73e38c6f9b4b9a06a50196cbd38cd9c69f11886af9d3cf9f","tokenwise_kld_bytes":16504,"tokenwise_kld_path":"/workspace/artifacts/qualification/glm53-custom-k4-tp2-runtime-v14-kld/tokenwise-kld.npy","tokenwise_kld_sha256":"5a2f0ae4495cb8e674d39bb751a3851e41482ff405e135f8b6eaac9492688ba9","top1_agreement":0.9384465070835368,"vocab_size":154880,"window_id":"final-0000"}