Instructions to use ishiki-labs/qwen3-8b-ami with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ishiki-labs/qwen3-8b-ami with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base_model, "ishiki-labs/qwen3-8b-ami")

Transformers

How to use ishiki-labs/qwen3-8b-ami with Transformers:

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

pipe = pipeline("text-generation", model="ishiki-labs/qwen3-8b-ami")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ishiki-labs/qwen3-8b-ami", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ishiki-labs/qwen3-8b-ami with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ishiki-labs/qwen3-8b-ami"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ishiki-labs/qwen3-8b-ami",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ishiki-labs/qwen3-8b-ami

SGLang

How to use ishiki-labs/qwen3-8b-ami 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 "ishiki-labs/qwen3-8b-ami" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ishiki-labs/qwen3-8b-ami",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ishiki-labs/qwen3-8b-ami" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ishiki-labs/qwen3-8b-ami",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ishiki-labs/qwen3-8b-ami with Docker Model Runner:
```
docker model run hf.co/ishiki-labs/qwen3-8b-ami
```

qwen3-8b-ami / README.md

kraken07

Update README.md

173460f verified 4 months ago

preview code

Raw

History Blame Contribute Delete

1.87 kB

	---
	base_model: Qwen/Qwen3-8B
	library_name: peft
	pipeline_tag: text-generation
	tags:
	- base_model:adapter:Qwen/Qwen3-8B
	- lora
	- transformers
	- turn-taking
	- multi-party-dialogue
	- ami
	- text-classification
	---

	# Qwen3-8B-AMI: Proactive Response Prediction in Multi-Party Dialogue

	LoRA adapter for Qwen/Qwen3-8B fine-tuned on the AMI meeting corpus for proactive response prediction in multi-party conversations. Given a conversational context and a current utterance, the model predicts whether a target speaker will SPEAK next or remain SILENT.

	## Model Details

	- Model type: LoRA adapter for causal language model (text classification / sequence classification)
	- Language(s): English
	- License: Apache 2.0
	- Finetuned from: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
	- AMI Corpus: Meeting recordings and transcripts: [AMI Corpus](https://groups.inf.ed.ac.uk/ami/corpus/)

	### Model Sources

	- Base model: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)


	## How to Get Started with the Model

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from peft import PeftModel

	base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
	model = PeftModel.from_pretrained(base_model, "kraken07/qwen3-8b-ami")
	tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")

	# Your input format should match training: context turns + current turn
	# Output: SPEAK or SILENT prediction for the target speaker
	```

	## Citation

	If you use this model, please cite our work:

	```bibtex
	@misc{bhagtani2026speakstaysilentcontextaware,
	title={Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue},
	author={Bhagtani, Kratika and Anand, Mrinal and Xu, Yu Chen and Yadav, Amit Kumar Singh},
	year={2026},
	archivePrefix={arXiv},
	url={https://arxiv.org/abs/2603.11409}
	}
	```