Instructions to use gold24k/v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gold24k/v1 with Transformers:

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

pipe = pipeline("text-generation", model="gold24k/v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gold24k/v1")
model = AutoModelForCausalLM.from_pretrained("gold24k/v1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use gold24k/v1 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gold24k/v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gold24k/v1"
# 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/v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gold24k/v1

SGLang

How to use gold24k/v1 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/v1" \
    --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/v1",
		"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/v1" \
        --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/v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gold24k/v1 with Docker Model Runner:
```
docker model run hf.co/gold24k/v1
```

Affine R1032 selective fallback SF1 (scale 0.50)

This is a standalone, merged BF16 checkpoint derived from unconst/Affine-5czsc2fc98-r1032-vera-odpo-midrank-hibeta-shortctx-ultraextra-ep4-midlr-merged. It applies a half-strength 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: 62dfb322fdce5873543bd92692ab4ecc3e13f941
Adapter scale at merge: 0.50
LoRA: r16, alpha64, dropout0, all linear layers
Objective: DPO, beta0.2, learning rate 2e-7, one 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 R1032 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	9	0.102951	0.5556
preserve	46	0.003387	0.5870

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: 374

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for gold24k/v1

Base model

vera6/affine-5g4yy75zuz-t6

Finetuned

unconst/Affine-5czsc2fc98-r1032-vera-odpo-midrank-hibeta-shortctx-ultraextra-ep4-midlr-merged

Finetuned

(2)

this model