Not-For-All-Audiences

abliterated

heretic

uncensor

hermes-lineage

Model card Files Files and versions

xet

Community

Instructions to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with Transformers:

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

pipe = pipeline("image-text-to-text", model="oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT")
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("oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT")
model = AutoModelForMultimodalLM.from_pretrained("oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT",
		"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/oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT

SGLang

How to use oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT 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 "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT" \
    --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": "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT",
		"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 "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT" \
        --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": "oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT",
		"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 oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT with Docker Model Runner:
```
docker model run hf.co/oktayd/Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT
```

Qwen3.6-35B-v2-MoE-Ablit-Heretic-Uncensor-Hermes-MTP-Vision-FT / BENCHMARK-TEST-COUNTS.json

oktayd

Explain MoE and inherited stages; add per-test benchmark dropdowns and laptop capability roadmap

9c72efb verified 19 days ago

Raw

History Blame Contribute Delete

34.1 kB

	{
	"schema_version": "q36.public-strict-counts.v1",
	"source_sha256": "9aef69af26b03d3b26a9250a1f6c21fdd4972a63522806d7724454b66b820b17",
	"scoring": "Original strict evaluator, not semantic regrade. Ungraded and incomplete may overlap.",
	"runs": [
	{
	"run": "q36-final-q4_k_m-llamacpp-h200",
	"model": "Q36",
	"device": "H200",
	"benchmarks": [
	{
	"benchmark": "ARC-Challenge",
	"planned": 10,
	"attempted": 10,
	"completed": 8,
	"scored": 8,
	"passed": 8,
	"ungraded": 2,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "BBH",
	"planned": 23,
	"attempted": 23,
	"completed": 20,
	"scored": 20,
	"passed": 3,
	"ungraded": 3,
	"not_run": 0,
	"incomplete": 3
	},
	{
	"benchmark": "ChartQA",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GPQA-Diamond",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 2,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GSM8K",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 9,
	"passed": 5,
	"ungraded": 1,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "HumanEval-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "IFEval",
	"planned": 10,
	"attempted": 10,
	"completed": 6,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 4
	},
	{
	"benchmark": "LiveCodeBench",
	"planned": 9,
	"attempted": 9,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 9,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MATH-Level-5",
	"planned": 10,
	"attempted": 10,
	"completed": 8,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "MBPP-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMLU-Pro",
	"planned": 1,
	"attempted": 1,
	"completed": 1,
	"scored": 1,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMMU",
	"planned": 6,
	"attempted": 6,
	"completed": 6,
	"scored": 6,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MathVista",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 2,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Agent-Function-Calling",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Answer-Termination-No-Looping",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 7,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Benign-Compliance-No-Overrefusal",
	"planned": 20,
	"attempted": 20,
	"completed": 18,
	"scored": 0,
	"passed": 0,
	"ungraded": 20,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "Q36-CAPTCHA-Detection-and-Handoff",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Contradiction-and-Anti-Sycophancy",
	"planned": 10,
	"attempted": 10,
	"completed": 8,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "Q36-Direct-Style-and-Personality",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "Q36-Hermes-Tool-Format",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-JSON-Schema",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Legal-Alternatives-and-Boundaries",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Output-Integrity",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "TruthfulQA",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 9,
	"passed": 6,
	"ungraded": 1,
	"not_run": 0,
	"incomplete": 1
	}
	]
	},
	{
	"run": "q36-final-q4_k_m-llamacpp-rtx5090",
	"model": "Q36",
	"device": "RTX 5090",
	"benchmarks": [
	{
	"benchmark": "ARC-Challenge",
	"planned": 10,
	"attempted": 10,
	"completed": 8,
	"scored": 8,
	"passed": 8,
	"ungraded": 2,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "BBH",
	"planned": 23,
	"attempted": 23,
	"completed": 20,
	"scored": 20,
	"passed": 3,
	"ungraded": 3,
	"not_run": 0,
	"incomplete": 3
	},
	{
	"benchmark": "ChartQA",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GPQA-Diamond",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 1,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GSM8K",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 7,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "HumanEval-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 4,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "IFEval",
	"planned": 10,
	"attempted": 10,
	"completed": 8,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "LiveCodeBench",
	"planned": 9,
	"attempted": 9,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 9,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MATH-Level-5",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "MBPP-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMLU-Pro",
	"planned": 1,
	"attempted": 1,
	"completed": 1,
	"scored": 1,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMMU",
	"planned": 6,
	"attempted": 6,
	"completed": 6,
	"scored": 6,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MathVista",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 2,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Agent-Function-Calling",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Answer-Termination-No-Looping",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 9,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Benign-Compliance-No-Overrefusal",
	"planned": 20,
	"attempted": 20,
	"completed": 18,
	"scored": 0,
	"passed": 0,
	"ungraded": 20,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "Q36-CAPTCHA-Detection-and-Handoff",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Contradiction-and-Anti-Sycophancy",
	"planned": 10,
	"attempted": 10,
	"completed": 8,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "Q36-Direct-Style-and-Personality",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Hermes-Tool-Format",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 3,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-JSON-Schema",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Legal-Alternatives-and-Boundaries",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Output-Integrity",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "TruthfulQA",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 9,
	"passed": 6,
	"ungraded": 1,
	"not_run": 0,
	"incomplete": 1
	}
	]
	},
	{
	"run": "huihui-original-q4_k_m-llamacpp-rtx5090",
	"model": "Huihui",
	"device": "RTX 5090",
	"benchmarks": [
	{
	"benchmark": "ARC-Challenge",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "BBH",
	"planned": 23,
	"attempted": 23,
	"completed": 23,
	"scored": 23,
	"passed": 16,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "ChartQA",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GPQA-Diamond",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GSM8K",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 7,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "HumanEval-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "IFEval",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "LiveCodeBench",
	"planned": 9,
	"attempted": 9,
	"completed": 4,
	"scored": 0,
	"passed": 0,
	"ungraded": 9,
	"not_run": 0,
	"incomplete": 5
	},
	{
	"benchmark": "MATH-Level-5",
	"planned": 10,
	"attempted": 10,
	"completed": 8,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "MBPP-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMLU-Pro",
	"planned": 1,
	"attempted": 1,
	"completed": 1,
	"scored": 1,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMMU",
	"planned": 6,
	"attempted": 6,
	"completed": 6,
	"scored": 6,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MathVista",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 3,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Agent-Function-Calling",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Answer-Termination-No-Looping",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Benign-Compliance-No-Overrefusal",
	"planned": 20,
	"attempted": 20,
	"completed": 20,
	"scored": 0,
	"passed": 0,
	"ungraded": 20,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-CAPTCHA-Detection-and-Handoff",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Contradiction-and-Anti-Sycophancy",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Direct-Style-and-Personality",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Hermes-Tool-Format",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-JSON-Schema",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 2,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Legal-Alternatives-and-Boundaries",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Output-Integrity",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "TruthfulQA",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 9,
	"passed": 6,
	"ungraded": 1,
	"not_run": 0,
	"incomplete": 1
	}
	]
	},
	{
	"run": "q36-final-q4_k_m-llamacpp-rtx2000ada-mixed24",
	"model": "Q36",
	"device": "RTX 2000 Ada (CPU+GPU)",
	"benchmarks": [
	{
	"benchmark": "ARC-Challenge",
	"planned": 10,
	"attempted": 10,
	"completed": 7,
	"scored": 7,
	"passed": 7,
	"ungraded": 3,
	"not_run": 0,
	"incomplete": 3
	},
	{
	"benchmark": "BBH",
	"planned": 23,
	"attempted": 23,
	"completed": 20,
	"scored": 20,
	"passed": 3,
	"ungraded": 3,
	"not_run": 0,
	"incomplete": 3
	},
	{
	"benchmark": "ChartQA",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GPQA-Diamond",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 2,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GSM8K",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 8,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "HumanEval-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "IFEval",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "LiveCodeBench",
	"planned": 9,
	"attempted": 9,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 9,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MATH-Level-5",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "MBPP-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMLU-Pro",
	"planned": 1,
	"attempted": 1,
	"completed": 1,
	"scored": 1,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMMU",
	"planned": 6,
	"attempted": 6,
	"completed": 6,
	"scored": 6,
	"passed": 1,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MathVista",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 3,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Agent-Function-Calling",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Answer-Termination-No-Looping",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 8,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Benign-Compliance-No-Overrefusal",
	"planned": 20,
	"attempted": 20,
	"completed": 19,
	"scored": 0,
	"passed": 0,
	"ungraded": 20,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "Q36-CAPTCHA-Detection-and-Handoff",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 9,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Contradiction-and-Anti-Sycophancy",
	"planned": 10,
	"attempted": 10,
	"completed": 9,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "Q36-Direct-Style-and-Personality",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Hermes-Tool-Format",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-JSON-Schema",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Legal-Alternatives-and-Boundaries",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Output-Integrity",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "TruthfulQA",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 6,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	}
	]
	},
	{
	"run": "huihui-original-q4_k_m-llamacpp-rtx2000ada-mixed24",
	"model": "Huihui",
	"device": "RTX 2000 Ada (CPU+GPU)",
	"benchmarks": [
	{
	"benchmark": "ARC-Challenge",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "BBH",
	"planned": 23,
	"attempted": 11,
	"completed": 10,
	"scored": 10,
	"passed": 6,
	"ungraded": 1,
	"not_run": 12,
	"incomplete": 1
	},
	{
	"benchmark": "ChartQA",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "GPQA-Diamond",
	"planned": 5,
	"attempted": 5,
	"completed": 3,
	"scored": 3,
	"passed": 3,
	"ungraded": 2,
	"not_run": 0,
	"incomplete": 2
	},
	{
	"benchmark": "GSM8K",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 7,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "HumanEval-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "IFEval",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "LiveCodeBench",
	"planned": 9,
	"attempted": 9,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 9,
	"not_run": 0,
	"incomplete": 4
	},
	{
	"benchmark": "MATH-Level-5",
	"planned": 10,
	"attempted": 10,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 5
	},
	{
	"benchmark": "MBPP-Plus",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 0,
	"passed": 0,
	"ungraded": 5,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MMLU-Pro",
	"planned": 1,
	"attempted": 1,
	"completed": 0,
	"scored": 0,
	"passed": 0,
	"ungraded": 1,
	"not_run": 0,
	"incomplete": 1
	},
	{
	"benchmark": "MMMU",
	"planned": 6,
	"attempted": 6,
	"completed": 6,
	"scored": 6,
	"passed": 4,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "MathVista",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 3,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Agent-Function-Calling",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 0,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Answer-Termination-No-Looping",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Benign-Compliance-No-Overrefusal",
	"planned": 20,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 10,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-CAPTCHA-Detection-and-Handoff",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 10,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Contradiction-and-Anti-Sycophancy",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Direct-Style-and-Personality",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Hermes-Tool-Format",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 3,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-JSON-Schema",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 3,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Legal-Alternatives-and-Boundaries",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 0,
	"passed": 0,
	"ungraded": 10,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "Q36-Output-Integrity",
	"planned": 5,
	"attempted": 5,
	"completed": 5,
	"scored": 5,
	"passed": 5,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	},
	{
	"benchmark": "TruthfulQA",
	"planned": 10,
	"attempted": 10,
	"completed": 10,
	"scored": 10,
	"passed": 7,
	"ungraded": 0,
	"not_run": 0,
	"incomplete": 0
	}
	]
	}
	]
	}