Instructions to use pottokao/MOSS-Image-Text-Encoder-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pottokao/MOSS-Image-Text-Encoder-Heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="pottokao/MOSS-Image-Text-Encoder-Heretic")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("pottokao/MOSS-Image-Text-Encoder-Heretic")
model = AutoModelForMultimodalLM.from_pretrained("pottokao/MOSS-Image-Text-Encoder-Heretic", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pottokao/MOSS-Image-Text-Encoder-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pottokao/MOSS-Image-Text-Encoder-Heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pottokao/MOSS-Image-Text-Encoder-Heretic",
		"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/pottokao/MOSS-Image-Text-Encoder-Heretic

SGLang

How to use pottokao/MOSS-Image-Text-Encoder-Heretic 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 "pottokao/MOSS-Image-Text-Encoder-Heretic" \
    --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": "pottokao/MOSS-Image-Text-Encoder-Heretic",
		"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 "pottokao/MOSS-Image-Text-Encoder-Heretic" \
        --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": "pottokao/MOSS-Image-Text-Encoder-Heretic",
		"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 pottokao/MOSS-Image-Text-Encoder-Heretic with Docker Model Runner:
```
docker model run hf.co/pottokao/MOSS-Image-Text-Encoder-Heretic
```

Different quants

by bobalabil22444 - opened about 22 hours ago

Discussion

bobalabil22444

about 22 hours ago

Any plan to add different quants version for safetensor format? Full bf16 are bit overkill for most users, would be nice to have INT8 or BF8 version

pottokao

Owner about 13 hours ago

Hugging Face CLI

Added INT8 versions (ComfyUI-native int8_tensorwise + ConvRot, same layout as Comfy-Org's Qwen3.5-9B files) under int8/:

moss_te_heretic_full_int8_convrot.safetensors (9.75 GB) — keeps lm_head/MTP/vision, works as both text encoder and prompt enhancer (TextGenerate).
moss_te_heretic_te_int8_convrot.safetensors (7.95 GB) — text-encoder only (no lm_head/MTP/vision); encoding is identical to the full one.

Encoding vs BF16 on 36 held-out prompts: mean rel. error 2.75%, cos ≥ 0.9988. For smaller files see the GGUF repo (down to ~3 GB). Thanks for the suggestion!

bobalabil22444

about 13 hours ago

Damn that was fast upload, much appreciated for the work

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment