Instructions to use elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1")
model = AutoModelForMultimodalLM.from_pretrained("elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-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": "elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1",
		"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/elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1

SGLang

How to use elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-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 "elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-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": "elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1",
		"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 "elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-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": "elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1",
		"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 elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1 with Docker Model Runner:
```
docker model run hf.co/elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1
```

JATS agentic annotation — Qwen3.5-9B teacher-distilled LoRA (v1, "tfull")

Full merged weights (Qwen3.5-9B + teacher-distilled LoRA) for a multi-turn tool-call agent emitting JATS XML for scientific-paper body sections via the scratchpad environment in agentic-jats-annotation-inference.

These are ready-to-serve full weights (LoRA already merged onto the v11 SFT base). The raw adapter is also included under lora_adapter/ — if you use it instead, apply it on top of the v11 SFT merge, NOT raw Qwen3.5-9B (measured: 0.234 vs 0.452 pass@6 body F).

Training

Teacher: DeepSeek-v4-pro driven turn-by-turn through the 17-tool JatsEnv on sup/sub-preserving markdown (docling + custom run/footnote/ins fixes); 1,549 rollouts over 800 docs (~~$250 API), filtered to best-per-doc with F0.5 ≥ 0.45 and recall ≥ 0.30 (~~430 trajectories).
SFT: LoRA r32/α64, lr 2e-5, 2 epochs, max-length 16384, assistant-token masking, bf16, sdpa attention (flash_attn_2 crashes on this architecture).

Evaluation (77-doc fixed body slice, strict exact-match metric, pass@6 @ T=0.9)

model	plain F	+ candidate merge	median F	mean single-rollout F
v11 SFT base	0.336	0.511	0.258	0.172
+ 215-doc teacher SFT	0.372	0.536	0.340	0.148
this adapter (~430 docs)	0.452	0.595	0.488	0.180

Paired vs base: +0.118 (95% CI +0.067..+0.169). Perfect-play ceiling under this metric is 0.842. "Candidate merge" = deterministic DOCX-style-run and regex-citation candidates union-merged post-hoc at serialize time (scripts/candidate_merge.py in the training repo); recommended in production. PDF-sourced inputs score lower (≈0.16 plain).

Serving

vLLM ≥ 0.19, --max-model-len 41472, thinking mode ON, temp 0.7–0.9; stop on </tool_call>, one call per turn, env owns the XML tree. See the inference repo for the full annotation loop. Eval evidence: eval_passk_tfull_v2slice.json (per-doc f_lists + full traces).

Per-tag evidence (also in this repo)

eval_pertag_comparison.json — base/tpwarm/tfull with paired bootstrap CIs (tfull vs base: +0.118 [+0.066,+0.172] plain; docx 0.487/0.632, pdf 0.294/0.429).
eval_pertag_by_tag.json — per-JATS-tag P/R/F1 of best rollouts, with and without candidate merge. Highlights (F1, plain → merged): sub 0.00 → 0.95, sup 0.34 → 0.54, xref 0.33 → 0.65.

Note for LoRA-only users: adapter_config.json:base_model_name_or_path refers to a local training path; the required base is the v11 scratchpad-SFT merge of Qwen/Qwen3.5-9B described above (not distributed here — contact the authors, or use the merged weights release when available).

Downloads last month: 10

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for elifepathways/jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Adapter

(1,073)

this model