Instructions to use gold24k/v7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gold24k/v7 with Transformers:

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

pipe = pipeline("text-generation", model="gold24k/v7")
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/v7")
model = AutoModelForMultimodalLM.from_pretrained("gold24k/v7", 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/v7 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gold24k/v7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gold24k/v7"
# 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/v7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gold24k/v7

SGLang

How to use gold24k/v7 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/v7" \
    --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/v7",
		"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/v7" \
        --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/v7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gold24k/v7 with Docker Model Runner:
```
docker model run hf.co/gold24k/v7
```

v7 (scale 0.50)

This is a standalone, merged BF16 checkpoint derived from unconstai/affine-5hndumbnxc-0c3c6cbec9. 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: 8cee08a200bf7ee6a643a29a842f99ab24f88d7c
Adapter scale at merge: 0.50
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: 80% preserve / 20% 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	18	0.169976	0.8333
preserve	65	0.038742	0.5692

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: 145

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for gold24k/v7

Base model

unconstai/affine-5hndumbnxc-0c3c6cbec9

Finetuned

(2)

this model