Instructions to use berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound with Transformers:

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

pipe = pipeline("image-text-to-text", model="berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound")
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("berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound")
model = AutoModelForMultimodalLM.from_pretrained("berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound", 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 berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound",
		"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/berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound

SGLang

How to use berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound 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 "berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound" \
    --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": "berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound",
		"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 "berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound" \
        --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": "berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound",
		"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 berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound with Docker Model Runner:
```
docker model run hf.co/berkerdooo/Qwen3.8-27B-Uncensored-INT8-AutoRound
```

berkerdooo commited on 10 days ago

Commit

7912c7e

verified ·

1 Parent(s): 7124105

extra_config: add .linear_attn. / .mtp.fc. 16-bit regex entries for SGLang fused-module matching

Browse files

Files changed (2) hide show

config.json +6 -0
quantization_config.json +6 -0

config.json CHANGED Viewed

@@ -984,6 +984,12 @@
       },
       ".*visual.*": {
         "bits": 16
       }
     },
     "gradient_accumulate_steps": 2,

       },
       ".*visual.*": {
         "bits": 16
+      },
+      ".*linear_attn.*": {
+        "bits": 16
+      },
+      ".*mtp\\.fc.*": {
+        "bits": 16
       }
     },
     "gradient_accumulate_steps": 2,

quantization_config.json CHANGED Viewed

@@ -977,6 +977,12 @@
     },
     ".*visual.*": {
       "bits": 16
     }
   }
 }

     },
     ".*visual.*": {
       "bits": 16
+    },
+    ".*linear_attn.*": {
+      "bits": 16
+    },
+    ".*mtp\\.fc.*": {
+      "bits": 16
     }
   }
 }

extra_config: add .*linear_attn.* / .*mtp.fc.* 16-bit regex entries for SGLang fused-module matching

extra_config: add .linear_attn. / .mtp.fc. 16-bit regex entries for SGLang fused-module matching