Instructions to use gold24k/v10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gold24k/v10 with Transformers:

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

pipe = pipeline("text-generation", model="gold24k/v10")
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/v10")
model = AutoModelForMultimodalLM.from_pretrained("gold24k/v10", 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/v10 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gold24k/v10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gold24k/v10"
# 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/v10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gold24k/v10

SGLang

How to use gold24k/v10 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/v10" \
    --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/v10",
		"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/v10" \
        --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/v10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gold24k/v10 with Docker Model Runner:
```
docker model run hf.co/gold24k/v10
```

v10 (scale 0.75)

This is a standalone, merged BF16 checkpoint derived from tojointhecommunity/affine-5efg6cm3yl-king. 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: 7c1c94cd0572475d4b3e3fde5258b0e79563d54f
Adapter scale at merge: 0.75
LoRA: r16, alpha32, dropout0.0, ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'in_proj_qkv', 'in_proj_z', 'in_proj_a', 'in_proj_b', 'out_proj']
Objective: DPO, beta0.2, learning rate 3.0e-08, 1.0 epoch
Context during training: 8192 tokens
Training GPUs: 2 x NVIDIA H200
Selected target mix before context filtering: 100% preserve / 0% 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	n/a	nan	nan
preserve	n/a	nan	nan

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: -

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for gold24k/v10

Base model

tojointhecommunity/affine-5efg6cm3yl-king

Finetuned

(2)

this model