Instructions to use Tdamre/Qwen3.5-0.8B-OCPI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tdamre/Qwen3.5-0.8B-OCPI with Transformers:

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

pipe = pipeline("text-generation", model="Tdamre/Qwen3.5-0.8B-OCPI")
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("Tdamre/Qwen3.5-0.8B-OCPI")
model = AutoModelForMultimodalLM.from_pretrained("Tdamre/Qwen3.5-0.8B-OCPI", 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 Tdamre/Qwen3.5-0.8B-OCPI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tdamre/Qwen3.5-0.8B-OCPI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tdamre/Qwen3.5-0.8B-OCPI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tdamre/Qwen3.5-0.8B-OCPI

SGLang

How to use Tdamre/Qwen3.5-0.8B-OCPI 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 "Tdamre/Qwen3.5-0.8B-OCPI" \
    --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": "Tdamre/Qwen3.5-0.8B-OCPI",
		"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 "Tdamre/Qwen3.5-0.8B-OCPI" \
        --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": "Tdamre/Qwen3.5-0.8B-OCPI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tdamre/Qwen3.5-0.8B-OCPI with Docker Model Runner:
```
docker model run hf.co/Tdamre/Qwen3.5-0.8B-OCPI
```

Qwen3.5-0.8B-OCPI

Finetune packaging of Qwen/Qwen3.5-0.8B as a full-weight OCPI operator field (not digests-only).

Method

Item	Value
Base model	`Qwen/Qwen3.5-0.8B`
Packaging	OCPI schema `ocpi.poc.qwen08b.v1`
Weights	float16 operator payload (488 tensors)
Projection	HOLO-style multi-view digests, 213419 blocks
corr_min	≈ 0.999965
corr_mean	≈ 0.999981
frac corr ≥ 0.9997	100%

This is an operator-field finetune packaging (method OCPI_FIELD in adapter_config.json): full base weights re-encoded for carrier/runtime use with projection ledger fidelity proofs. It is not a LoRA adapter.

Files

model.safetensors — full f16 weights (export from OCPI field)
config.json, tokenizer files — inference config
adapter_config.json — hub-facing finetune metadata
Optional companion: ocpi_field/ (binary lattice + events)

Multi-arch runtime

Standalone Rust binary ocpi-qwen is published for:

Windows: x86_64, i686, ARM64
Linux: x86_64, i686, aarch64
macOS: x86_64 + Apple Silicon with Metal feature

ocpi-qwen verify --field ocpi_field --lattice
ocpi-qwen chat --field ocpi_field --prompt "Hello"
ocpi-qwen export-hf --field ocpi_field --out ./

Transformers load

from transformers import AutoModelForImageTextToText, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained(".", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    ".", trust_remote_code=True, torch_dtype=torch.float16
)
messages = [{"role": "user", "content": "Hello! Who are you?"}]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(text, return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=48)
print(tok.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Citation

Base model: Qwen Team — Qwen3.5. OCPI field packaging: local PoC (ocpi.poc.qwen08b.v1).

Downloads last month: 281

Safetensors

Model size

0.9B params

Tensor type

F16

Model tree for Tdamre/Qwen3.5-0.8B-OCPI

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

(312)

this model