Instructions to use barozp/Qwen3.8-27B-Opus-Distill-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barozp/Qwen3.8-27B-Opus-Distill-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="barozp/Qwen3.8-27B-Opus-Distill-v2")
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("barozp/Qwen3.8-27B-Opus-Distill-v2")
model = AutoModelForMultimodalLM.from_pretrained("barozp/Qwen3.8-27B-Opus-Distill-v2", 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 barozp/Qwen3.8-27B-Opus-Distill-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barozp/Qwen3.8-27B-Opus-Distill-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "barozp/Qwen3.8-27B-Opus-Distill-v2",
		"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/barozp/Qwen3.8-27B-Opus-Distill-v2

SGLang

How to use barozp/Qwen3.8-27B-Opus-Distill-v2 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 "barozp/Qwen3.8-27B-Opus-Distill-v2" \
    --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": "barozp/Qwen3.8-27B-Opus-Distill-v2",
		"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 "barozp/Qwen3.8-27B-Opus-Distill-v2" \
        --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": "barozp/Qwen3.8-27B-Opus-Distill-v2",
		"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 barozp/Qwen3.8-27B-Opus-Distill-v2 with Docker Model Runner:
```
docker model run hf.co/barozp/Qwen3.8-27B-Opus-Distill-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.8-27B-Opus-Distill-v2

Qwen/Qwen3.8-27B fine-tuned (LoRA, merged) on verified-genuine Claude Opus reasoning traces. This release fixes a reasoning-loop bug reported against the first release (barozp/Qwen3.8-27B-Opus-Distill, "v1") while keeping the reasoning-quality gains v1 was known for.

Why this release exists

A community member (zxbc2023) reported a clean, deterministic bug on v1: certain stacked output-format constraints (most notably "no prose" combined with a second constraint like "no markdown") sent the model into a non-converging self-verification loop — burning the entire token budget on repeated "wait, let me re-check…" passes with zero visible output. Their repro was exact and reproducible at temp=0, and they correctly diagnosed it as likely inherited from the distillation data rather than a capability gap. Full credit to them for the report that made this fix possible.

Root cause. Investigating v1's training data (opus-reasoning-distill-train) showed that 83% of it had actually been sourced from Jackrong's TraceInversion datasets — reasoning traces reconstructed by a small auxiliary model (Trace-Inverter-4B) from a compressed summary, not the teacher model's real output (openly documented on those datasets' own cards). That reconstruction process appears to have baked in a rigid "enumerate constraints, then re-verify" template — plausibly both the source of v1's reasoning-quality gains and the loop bug, two sides of the same mechanism.

The fix, in two steps:

First attempt: retrain purely on a genuine-trace dataset (lordx64/reasoning-distill-claude-opus-4-7-max). This fixed the loop bug completely but collapsed the reasoning-transfer gain (GPQA-Diamond dropped back to base/random level) — the domain mix mattered as much as trace authenticity.
This release: reconstructed v1's exact prompt distribution, but replaced every row traced back to Jackrong's fabricated sets with the verified genuine trace for the same prompt (from lordx64 or Roman1111111/claude-opus-4.6-10000x). Then ran a full-dataset scan (30 parallel LLM-judge passes over all 14,250 rows) for the specific pathological pattern and removed every flagged row (169) plus every row whose source was never verified against a known-genuine dataset (2,429). Net: 14,250 → 11,716 rows, 100% traced to verified sources.

Bug fix validation

Re-ran zxbc2023's exact repro (temp=0, seed=1234, fib(n) with stacked constraints) against this model:

Test	v1	v2
"no prose" + "no markdown"	3000/3000 tokens, 0 visible output	87/4096 tokens, clean code
"no prose" + "no comments"	3000/3000 tokens, 0 visible output	73/4096 tokens, clean code
Generalization (different task, same constraints)	—	43/4096 tokens, clean code

All three converge quickly with </think> closing normally — no loop, no budget exhaustion.

Benchmark results

Measured with lm-evaluation-harness, 0-shot, loglikelihood (multiple-choice), chat template OFF, QUICK mode (--limit 500) — identical protocol to v1, so the Δ column is the meaningful signal.

Task	Metric	Base	v2	Δ	(v1's Δ, for reference)
wikitext	word perplexity ↓	8.4335	8.3788	−0.055	−0.09
mmlu	acc	0.8494	0.8476	−0.002	−0.001
hellaswag	acc_norm	0.7420	0.7500	+0.008	−0.002
arc_challenge	acc_norm	0.5880	0.6220	+0.034	+0.042
gpqa_diamond	acc_norm	0.2323	0.4697	+0.237	+0.263

Reading the table: knowledge (MMLU) and language modeling (wikitext) are unaffected; reasoning (ARC, GPQA) shows a large, real gain — slightly smaller than v1's (expected: v1's gain was partly driven by the same fabricated content that caused the bug), but still far above noise. GPQA in particular is a same-protocol delta vs. base, not comparable to Qwen's own published 89.2 (thinking-mode-on, different harness) — see v1's card for the full caveat.

Model overview

Base model: Qwen/Qwen3.8-27B — dense 27B, native vision-language, native MTP.
Method: LoRA (r=64, alpha=64, dropout=0.05), merged into the base weights.
LoRA targets: attention q/k/v/o_proj on the 16 full-attention layers only; FFN gate/up/down_proj on all 64 layers.
Training data: barozp/opus-reasoning-distill-v2 (11,716 examples, 100% verified-genuine Opus traces).
Training run: 1 epoch (696 steps), lr=1e-4 cosine with 3% warmup, effective batch 16, MAX_SEQ=4096, bf16, ~4h15m on an A100 80GB.
Final validation loss: 0.4334 — lower than both v1 (0.4647) and the intermediate pure-genuine attempt (0.805), despite less data.
Vision + MTP: carried over from base, never trained.

Quick start

from transformers import AutoModelForImageTextToText, AutoProcessor
import torch

model = AutoModelForImageTextToText.from_pretrained(
    "barozp/Qwen3.8-27B-Opus-Distill-v2", dtype=torch.bfloat16, device_map="auto",
)
processor = AutoProcessor.from_pretrained("barozp/Qwen3.8-27B-Opus-Distill-v2")

Text-only inference also works via AutoModelForCausalLM.

Qwen3.8-27B — the base model.
barozp/Qwen3.8-27B-Opus-Distill — v1. Still works well for most use cases; this release specifically fixes the stacked-constraint reasoning-loop edge case.
barozp/opus-reasoning-distill-v2 — the training dataset, with full provenance notes.
Thanks to zxbc2023 for the bug report that led to this release.

Downloads last month: 18

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for barozp/Qwen3.8-27B-Opus-Distill-v2

Base model

Qwen/Qwen3.8-27B

Finetuned

(124)

this model

Quantizations

1 model

Collection including barozp/Qwen3.8-27B-Opus-Distill-v2

Qwen3.8-27B-Opus-Distill

Collection

6 items • Updated about 17 hours ago • 2

barozp
/

Qwen3.8-27B-Opus-Distill-v2