Instructions to use Jackrong/Qwopus3.8-27B-Flash-V2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jackrong/Qwopus3.8-27B-Flash-V2-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="Jackrong/Qwopus3.8-27B-Flash-V2-GGUF")
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 AutoModel
model = AutoModel.from_pretrained("Jackrong/Qwopus3.8-27B-Flash-V2-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jackrong/Qwopus3.8-27B-Flash-V2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jackrong/Qwopus3.8-27B-Flash-V2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jackrong/Qwopus3.8-27B-Flash-V2-GGUF",
		"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/Jackrong/Qwopus3.8-27B-Flash-V2-GGUF

SGLang

How to use Jackrong/Qwopus3.8-27B-Flash-V2-GGUF 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 "Jackrong/Qwopus3.8-27B-Flash-V2-GGUF" \
    --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": "Jackrong/Qwopus3.8-27B-Flash-V2-GGUF",
		"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 "Jackrong/Qwopus3.8-27B-Flash-V2-GGUF" \
        --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": "Jackrong/Qwopus3.8-27B-Flash-V2-GGUF",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Jackrong/Qwopus3.8-27B-Flash-V2-GGUF with Docker Model Runner:
```
docker model run hf.co/Jackrong/Qwopus3.8-27B-Flash-V2-GGUF
```

Jackrong commited on 13 days ago

Commit

65c8e48

verified ·

1 Parent(s): 85ef570

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -1

README.md CHANGED Viewed

@@ -40,7 +40,7 @@ base_model_relation: finetune
 # 🪐 Qwopus3.8-27B-Flash-V2
 <div align="center">
-<img src="https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/GvN4SANiFepBuWcsoWbOX.jpeg" alt="Qwopus model artwork" width="82%"/>
 </div>
 > [!NOTE]
@@ -68,6 +68,21 @@ V2 keeps this efficiency-oriented philosophy while applying another round of pos
 The objective is to reduce ineffective computation and reach a clean completion more quickly and consistently. Efficiency remains an explicit trade-off: a shorter reasoning trace is useful only when the model still completes the task correctly. The benchmark sections below report the measured scope of that trade-off.
 ## 🧪 2. Fine-Tuning Cookbook
 ### 2.1 Base Model and Training Lineage

 # 🪐 Qwopus3.8-27B-Flash-V2
 <div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/UBRjhjok17Kvz-NA03VoD.jpeg" alt="IMG_7359" width="82%"/>
 </div>
 > [!NOTE]
 The objective is to reduce ineffective computation and reach a clean completion more quickly and consistently. Efficiency remains an explicit trade-off: a shorter reasoning trace is useful only when the model still completes the task correctly. The benchmark sections below report the measured scope of that trade-off.
+### Five-Story Pagoda Garden — Visual Output Comparison
+> [!NOTE]
+> These visuals are qualitative model outputs. They complement the measured benchmark results below and are not a quantitative capability score on their own.
+#### Original Base Model — Qwen3.8-27B
+![Original model — Five-Story Pagoda test](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/r2jq2T2BEdtQJMYCMaMzR.png)
+#### Fine-Tuned Model — Qwopus3.8-27B-Flash-V2
+![Fine-tuned model — Five-Story Pagoda test](https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/7YGeM1vEeJgS7wDXcz3eq.png)
 ## 🧪 2. Fine-Tuning Cookbook
 ### 2.1 Base Model and Training Lineage