Instructions to use gold24k/v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gold24k/v5 with Transformers:

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

pipe = pipeline("text-generation", model="gold24k/v5")
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("gold24k/v5")
model = AutoModelForMultimodalLM.from_pretrained("gold24k/v5", 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]:]))

PEFT
How to use gold24k/v5 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gold24k/v5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gold24k/v5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gold24k/v5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gold24k/v5

SGLang

How to use gold24k/v5 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 "gold24k/v5" \
    --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": "gold24k/v5",
		"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 "gold24k/v5" \
        --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": "gold24k/v5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gold24k/v5 with Docker Model Runner:
```
docker model run hf.co/gold24k/v5
```

v5 (scale 1.00)

This is a standalone, merged BF16 checkpoint derived from gold24k/v3. It applies a scaled selective-fallback LoRA trained on preserved positive turns and sanitized, task-specific alternatives for high-confidence negative turns. It does not require a runtime router, custom Python code, or a PEFT adapter.

Training summary

Exact parent revision: 698c1fa8fa42e8c60ba44c6fd7d5b48e8c72b489
Adapter scale at merge: 1.00
LoRA: r16, alpha64, dropout0.0, all-linear
Objective: DPO, beta0.2, learning rate 2.0e-08, 1.0 epoch
Context during training: 8192 tokens
Training GPUs: 2 x NVIDIA H200
Selected target mix before context filtering: 90% preserve / 10% fallback

Held-out preference proxy

The table compares the scaled adapter with the untouched pinned parent. These small held-out metrics selected the merge strength; they are not a substitute for the exact full Affine duel on the dedicated evaluator.

route	rows	mean reward margin	preference accuracy
fallback	7	0.107690	0.5714
preserve	46	0.062635	0.6087

Qualification status

Experimental candidate. Before submission, run exact stock-vLLM Affine duels, the exploit-pattern audit, repository preflight, and the official submission client check. selective_fallback_provenance.json contains the machine-readable training and merge record.

Downloads last month: 216

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for gold24k/v5

Base model

unconstai/affine-5hndumbnxc-0c3c6cbec9

Finetuned

gold24k/v3

Finetuned

(1)

this model