Instructions to use timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16")
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("timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16")
model = AutoModelForMultimodalLM.from_pretrained("timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16", 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 timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16",
		"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/timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16

SGLang

How to use timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16 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 "timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16" \
    --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": "timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16",
		"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 "timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16" \
        --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": "timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16",
		"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 timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16 with Docker Model Runner:
```
docker model run hf.co/timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16
```

Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16 / RELEASE_FAMILY.md

timteh673

Publish release card, license, benchmarks, and integrity manifests

2e762e9 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

3.71 kB

Qwen3.8-27B Opus personal-model release family

This four-repository family publishes the selected practical winner and its immutable trained-control comparator in BF16 and Apple-Silicon MLX 8-bit formats. The recommended default is the MLX 8-bit winner.

Selection language: practical personal-model selection with measured deviations. This release does not claim universal dominance or that every strict gate passed.

Repository	Role	Format	Public model files	Public model bytes
Qwen3.8-27B-Opus-Abliterix-Reasoning-MLX-8bit	Recommended practical winner	MLX 8-bit	17	30,390,836,635
Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16	Full-precision practical winner	BF16 Transformers	10	55,583,125,224
Qwen3.8-27B-Opus-Reasoning-Control-MLX-8bit	Baseline comparator	MLX 8-bit	17	30,390,836,197
Qwen3.8-27B-Opus-Reasoning-Control-BF16	Full-precision baseline comparator	BF16 Transformers	20	55,583,123,681

Lineage

Qwen/Qwen3.8-27B → reasoning QLoRA merge (control-bf16) → Abliterix pass 1 (abliterix-pass1-bf16) → BF16 and affine MLX 8-bit/group-64 release variants.

Dataset preparation started from 12,842 raw rows and accepted 12,614 after 208 deduplications and 20 invalid-row removals; splits were 12,349 train / 127 validation / 138 test. Training used 1,544 optimizer steps, 108,789,760 trainable LoRA parameters, final validation loss 0.23739749, and token accuracy 91.7594%. The merged model retained 1,199 tensor keys, 15 native MTP tensors, and 333 vision tensors. The winner has 74 verified residual-writer edits and zero unexpected changes.

Local benchmark headline

These are self-run frozen local benchmarks, not official Qwen benchmarks.

Frozen local metric	Control	Abliterix winner
Harmful hard refusal	43.2%	0.0%
Harmful soft deflection	14.6%	0.2%
Harmful substantive response	47.0%	99.4%
Capability macro	17.6859%	21.0086%
Full code	16/421	10/421
HumanEval	7.9268%	4.2683%
Long-form pass	54.1667%	62.5000%
MMMU30	9/30	11/30
Held-out loss ratio	1.000000	1.024478
Benign KL	0.000000	0.093614

Strict deviations remain part of the release: KL 0.093614 > 0.05; incoherence 4.3077% > 2.7692%; HumanEval 4.2683% versus 7.9268%; full code 10/421 versus 16/421; repetition 5.8632% > 5%; prompt leakage detected; and 376/421 winner code generations hit the 512-token cap. Among outputs reaching execution, winner pass rate was 10/46 (21.74%) versus control 16/103 (15.53%), indicating termination/extraction pathology rather than a clean latent-code estimate.

The canonical structured record is benchmark-results.json.

Packaging boundary

Model weights and runtime metadata come from sealed source artifacts. Public manifests were regenerated from verified SHA-256/size receipts. Local paths, private prompt/training data, Drive identifiers, operational receipts, and internal release-control files are excluded. Each repository has a public per-file SHA256SUMS and manifests/artifact-manifest.json.

timteh673
/

Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16

Qwen3.8-27B Opus personal-model release family

Lineage

Local benchmark headline

Packaging boundary

License