Instructions to use ReBatch/Qwen3.8-27B-Weight-Space-Programming with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ReBatch/Qwen3.8-27B-Weight-Space-Programming with Transformers:

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

pipe = pipeline("image-text-to-text", model="ReBatch/Qwen3.8-27B-Weight-Space-Programming")
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("ReBatch/Qwen3.8-27B-Weight-Space-Programming")
model = AutoModelForMultimodalLM.from_pretrained("ReBatch/Qwen3.8-27B-Weight-Space-Programming", 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 ReBatch/Qwen3.8-27B-Weight-Space-Programming with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ReBatch/Qwen3.8-27B-Weight-Space-Programming"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReBatch/Qwen3.8-27B-Weight-Space-Programming",
		"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/ReBatch/Qwen3.8-27B-Weight-Space-Programming

SGLang

How to use ReBatch/Qwen3.8-27B-Weight-Space-Programming 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 "ReBatch/Qwen3.8-27B-Weight-Space-Programming" \
    --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": "ReBatch/Qwen3.8-27B-Weight-Space-Programming",
		"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 "ReBatch/Qwen3.8-27B-Weight-Space-Programming" \
        --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": "ReBatch/Qwen3.8-27B-Weight-Space-Programming",
		"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 ReBatch/Qwen3.8-27B-Weight-Space-Programming with Docker Model Runner:
```
docker model run hf.co/ReBatch/Qwen3.8-27B-Weight-Space-Programming
```

JorgeDeC commited on 9 days ago

Commit

41bff11

verified ·

1 Parent(s): 6df2ccc

Remove requested introductory paragraph from model card

Browse files

Files changed (2) hide show

README.md +0 -2
SHA256SUMS +1 -1

README.md CHANGED Viewed

@@ -17,8 +17,6 @@ tags:
 This is ReBatch's experimental weight-edited derivative of [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B). A sparse edit to one MLP output projection lowers the model's local full-set CCPBench-A mean from **2.714 to 1.518**. The same checkpoint has lower point estimates on IFBench, HumanEval, HumanEval+, oracle FinanceBench, and the Omniscience index. Omniscience accuracy increases slightly.
-**This release demonstrates a measured tradeoff. Capability preservation was not achieved, and 1.518 is above the original exact 1.50 target.** A lower CCPBench score does not establish greater truthfulness, political neutrality, adoption of “Western values,” or a general improvement in alignment.
 ## Model identity
 | Item | Recorded value |

 This is ReBatch's experimental weight-edited derivative of [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B). A sparse edit to one MLP output projection lowers the model's local full-set CCPBench-A mean from **2.714 to 1.518**. The same checkpoint has lower point estimates on IFBench, HumanEval, HumanEval+, oracle FinanceBench, and the Omniscience index. Omniscience accuracy increases slightly.
 ## Model identity
 | Item | Recorded value |

SHA256SUMS CHANGED Viewed

@@ -1,7 +1,7 @@
 c1f807b4d810609bf2efe6011cecf5cf7c3a13794e4c0b225df8532b301054d0  CHECKPOINT_VERIFICATION.json
 bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a  LICENSE
 a491d6ec87c13b4478511f6ac7658973633ad7e1ab21578c09efeab72f3e9c9c  MODIFICATIONS.md
-205270e9c1dc4eb515d7353b52e823fc684f7dcc0a7aa2b169410eddd8e6c185  README.md
 c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041  chat_template.jinja
 191e0af232104ed8b65258cf3fb2b842e288008baca7633c11b82a1ac7203aab  config.json
 4d62467f5f7b4a00a820b7fe8217f8380c78bbd06c5d9312a623e3f3f8144894  evaluation_results.json

 c1f807b4d810609bf2efe6011cecf5cf7c3a13794e4c0b225df8532b301054d0  CHECKPOINT_VERIFICATION.json
 bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a  LICENSE
 a491d6ec87c13b4478511f6ac7658973633ad7e1ab21578c09efeab72f3e9c9c  MODIFICATIONS.md
+b7ed8d09f991ee00156c15f72f26180c2a428edab5e5a2ba4fc4b6d3117ee81a  README.md
 c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041  chat_template.jinja
 191e0af232104ed8b65258cf3fb2b842e288008baca7633c11b82a1ac7203aab  config.json
 4d62467f5f7b4a00a820b7fe8217f8380c78bbd06c5d9312a623e3f3f8144894  evaluation_results.json