Instructions to use dolev31/ProactiveInquirer-Qwen3-8B-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dolev31/ProactiveInquirer-Qwen3-8B-Merged with Transformers:

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

pipe = pipeline("text-generation", model="dolev31/ProactiveInquirer-Qwen3-8B-Merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dolev31/ProactiveInquirer-Qwen3-8B-Merged")
model = AutoModelForCausalLM.from_pretrained("dolev31/ProactiveInquirer-Qwen3-8B-Merged", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dolev31/ProactiveInquirer-Qwen3-8B-Merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dolev31/ProactiveInquirer-Qwen3-8B-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dolev31/ProactiveInquirer-Qwen3-8B-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dolev31/ProactiveInquirer-Qwen3-8B-Merged

SGLang

How to use dolev31/ProactiveInquirer-Qwen3-8B-Merged 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 "dolev31/ProactiveInquirer-Qwen3-8B-Merged" \
    --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": "dolev31/ProactiveInquirer-Qwen3-8B-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "dolev31/ProactiveInquirer-Qwen3-8B-Merged" \
        --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": "dolev31/ProactiveInquirer-Qwen3-8B-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dolev31/ProactiveInquirer-Qwen3-8B-Merged with Docker Model Runner:
```
docker model run hf.co/dolev31/ProactiveInquirer-Qwen3-8B-Merged
```

dolev31 commited on 12 days ago

Commit

45b629e

verified ·

1 Parent(s): b6e8077

Card: Results and Limitations sections, pointing to the adapter card's results

Browse files

Files changed (1) hide show

README.md +16 -0

README.md CHANGED Viewed

@@ -50,6 +50,12 @@ This is training seed 1, the adapter at the root of the adapter repository. The
 and the weights are stored in bfloat16. On the adapter card's two-turn example, greedy decoding with
 this model returns the adapter's output character for character.
 ## How to use it
 The questioner reads the prompt template it was trained on, in [`prompts/`](prompts/), and replies
@@ -102,6 +108,16 @@ vllm serve dolev31/ProactiveInquirer-Qwen3-8B-Merged
 #                "chat_template_kwargs": {"enable_thinking": false}, "temperature": 0}
 ```
 ## Citation
 ```bibtex

 and the weights are stored in bfloat16. On the adapter card's two-turn example, greedy decoding with
 this model returns the adapter's output character for character.
+## Results
+The results are the trained questioner's, as the paper reports them: see the
+[adapter card's Results](https://huggingface.co/dolev31/ProactiveInquirer-Qwen3-8B#results). This merged model reproduces the adapter's output on that card's example, as the paragraph
+above says.
 ## How to use it
 The questioner reads the prompt template it was trained on, in [`prompts/`](prompts/), and replies
 #                "chat_template_kwargs": {"enable_thinking": false}, "temperature": 0}
 ```
+## Limitations
+- The questioner's own limitations, from the paper: it has learned what to ask more readily than when to
+  stop, the extra evidence it finds does not yet translate into better final answers, and its user-facing
+  results come from a simulated customer, not from real people.
+- It is a component inside an agent, meant to be called with its prompt template. It is not a chat
+  assistant, and it was trained and evaluated in English.
+- This is one training seed (seed 1), merged in float32 and stored in bfloat16. Its equality with the
+  adapter was checked on the card's example, not on a benchmark.
 ## Citation
 ```bibtex