Instructions to use chjdl1816/designcoder-mc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chjdl1816/designcoder-mc with Transformers:

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

pipe = pipeline("image-text-to-text", model="chjdl1816/designcoder-mc")
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("chjdl1816/designcoder-mc")
model = AutoModelForMultimodalLM.from_pretrained("chjdl1816/designcoder-mc", 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 chjdl1816/designcoder-mc with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chjdl1816/designcoder-mc"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chjdl1816/designcoder-mc",
		"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/chjdl1816/designcoder-mc

SGLang

How to use chjdl1816/designcoder-mc 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 "chjdl1816/designcoder-mc" \
    --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": "chjdl1816/designcoder-mc",
		"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 "chjdl1816/designcoder-mc" \
        --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": "chjdl1816/designcoder-mc",
		"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 chjdl1816/designcoder-mc with Docker Model Runner:
```
docker model run hf.co/chjdl1816/designcoder-mc
```

designcoder-mc / merge_validation.json

chjdl1816

Publish selected local AdamW 4B SFT step12588, merged BF16 plus original LoRA

f1c28f5 verified 3 days ago

Raw History Blame Contribute Delete

1.49 kB

{
  "method": "PEFT merge_and_unload(safe_merge=True), FP32 merge then BF16 export",
  "device": "cpu",
  "versions": {
    "torch": "2.6.0+cu124",
    "transformers": "5.8.0",
    "peft": "0.18.1",
    "safetensors": "0.7.0"
  },
  "adapter_tensor_count": 496,
  "all_adapter_tensors_loaded_exactly": true,
  "merged_parameter_count": 4539265536,
  "fp32_pre_post_merge_max_logit_error": 2.4020672e-05,
  "fp32_pre_post_merge_all_argmax_equal": true,
  "bf16_export_reload_logits_bitwise_equal": true,
  "fp32_runtime_buffers_preserved": [
    "model.visual.rotary_pos_emb.inv_freq",
    "model.language_model.rotary_emb.inv_freq",
    "model.language_model.rotary_emb.original_inv_freq"
  ],
  "tokenizer_vocab_matches_base_and_checkpoint": true,
  "processor_class": "Qwen3VLProcessor",
  "base_and_merged_loading_checks_passed": true,
  "execution_evidence": [
    "16:37:42 All 496 adapter tensors loaded exactly; checking forward before merge",
    "16:38:20 Merge validated: max logit error=2.4020672e-05; all token argmax equal",
    "16:39:20 Export reload is exact; tokenizer and processor load successfully"
  ],
  "validation_script_sha256": "453e8386a079b6dd651c1f19c5e61e0886a0799a94d9e0482703f4da09bc0a90",
  "metadata_note": "Completed validation metadata from successful assertion log after JSON serialization of an empty loading-info set failed. Numerical error is rounded as printed in that log.",
  "scope": "One short text prompt; no benchmark or GPU/vLLM validation."
}

	{
	"method": "PEFT merge_and_unload(safe_merge=True), FP32 merge then BF16 export",
	"device": "cpu",
	"versions": {
	"torch": "2.6.0+cu124",
	"transformers": "5.8.0",
	"peft": "0.18.1",
	"safetensors": "0.7.0"
	},
	"adapter_tensor_count": 496,
	"all_adapter_tensors_loaded_exactly": true,
	"merged_parameter_count": 4539265536,
	"fp32_pre_post_merge_max_logit_error": 2.4020672e-05,
	"fp32_pre_post_merge_all_argmax_equal": true,
	"bf16_export_reload_logits_bitwise_equal": true,
	"fp32_runtime_buffers_preserved": [
	"model.visual.rotary_pos_emb.inv_freq",
	"model.language_model.rotary_emb.inv_freq",
	"model.language_model.rotary_emb.original_inv_freq"
	],
	"tokenizer_vocab_matches_base_and_checkpoint": true,
	"processor_class": "Qwen3VLProcessor",
	"base_and_merged_loading_checks_passed": true,
	"execution_evidence": [
	"16:37:42 All 496 adapter tensors loaded exactly; checking forward before merge",
	"16:38:20 Merge validated: max logit error=2.4020672e-05; all token argmax equal",
	"16:39:20 Export reload is exact; tokenizer and processor load successfully"
	],
	"validation_script_sha256": "453e8386a079b6dd651c1f19c5e61e0886a0799a94d9e0482703f4da09bc0a90",
	"metadata_note": "Completed validation metadata from successful assertion log after JSON serialization of an empty loading-info set failed. Numerical error is rounded as printed in that log.",
	"scope": "One short text prompt; no benchmark or GPU/vLLM validation."
	}