Instructions to use visproj/lantern-1.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use visproj/lantern-1.7b with Transformers:

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

pipe = pipeline("text-generation", model="visproj/lantern-1.7b")
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("visproj/lantern-1.7b")
model = AutoModelForCausalLM.from_pretrained("visproj/lantern-1.7b", 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 visproj/lantern-1.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "visproj/lantern-1.7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "visproj/lantern-1.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/visproj/lantern-1.7b

SGLang

How to use visproj/lantern-1.7b 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 "visproj/lantern-1.7b" \
    --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": "visproj/lantern-1.7b",
		"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 "visproj/lantern-1.7b" \
        --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": "visproj/lantern-1.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use visproj/lantern-1.7b with Docker Model Runner:
```
docker model run hf.co/visproj/lantern-1.7b
```

lantern-1.7b / README.md

visproj

Rename lantern-1.7b-README.md to README.md

4fc0bbe verified 18 days ago

preview code

Raw History Blame Contribute Delete

3.08 kB

---
license: apache-2.0
base_model: Qwen/Qwen3-1.7B
datasets:
- visproj/lantern-episodes
pipeline_tag: text-generation
library_name: transformers
tags:
- agents
- tool-use
- distillation
- nethack
- minihack
---
# Lantern-1.7B

A 1.7B model that plays dungeon levels by calling tools, distilled from [Beam](https://huggingface.co/reflection/Beam-1.0-501B-A23B). It's the student half of [Lantern](https://huggingface.co/spaces/visproj/lantern).

## How it was made

- **Base model:** [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) (Apache-2.0).
- **Teacher:** Beam 1.0 by Reflection (Apache-2.0). Beam's model card states that Reflection doesn't prohibit distillation or using its outputs to train other models.
- **Data:** every Beam call from the winning episodes of the Lantern benchmark: 1,031 examples from 58 episodes across 8 MiniHack levels. Each example is the exact system prompt and observation Beam saw, and the tool calls it made (`act` with a list of moves, and `write_notes`). Only episodes with the current prompt version are used, and runs where a person coached the agent are left out. Data: [visproj/lantern-episodes](https://huggingface.co/datasets/visproj/lantern-episodes).
- **Training:** supervised fine-tuning with TRL, loss on the completion only, 3 epochs, learning rate 1e-5 (cosine), effective batch size 16, bf16, on one A100. Final training loss 0.37. Qwen3's thinking mode is turned off: the student answers with a tool call directly, without Beam's reasoning.

## Results

Same 8 MiniHack levels × 5 seeds, same prompt and tools, no journal:

| Model | Wins |
|---|---|
| Beam 1.0 (501B, teacher) | 23 / 40 |
| **Lantern-1.7B** | **11 / 40** |
| Qwen3-1.7B, untrained | 2 / 40 |

Per level, the student won Small Room 5/5, Room with Monsters 2/5, Memento 2/5, Key Room 1/5 and Corridors 1/5, and none of River Crossing, Maze Walk or Hide and Seek. Full per-level tables are in the [Space README](https://huggingface.co/spaces/visproj/lantern).

## How to use it

The model expects Lantern's prompt format and tool schema. Both are in the dataset: each episode's `start` event holds the exact system prompt and tool schema, and each `turn` event holds the observation prompt the model saw.

Serve it with vLLM and send requests in that format, with thinking turned off:

```bash
vllm serve visproj/lantern-1.7b --enable-auto-tool-choice --tool-call-parser hermes
```

Pass `{"chat_template_kwargs": {"enable_thinking": false}}` in the request body. The model replies with `act` or `write_notes` tool calls.

## Limitations

- It learned only from Beam's wins, so it has seen far fewer examples of recovering from mistakes than of clean play.
- It doesn't reason before acting the way Beam does, which matters most on the long levels.
- It's trained on Lantern's exact observation format. Other prompts or games will need retraining.
- 1,031 examples is a small dataset. Treat this as a proof of concept.

## License

Apache-2.0, as a fine-tune of Qwen3-1.7B (Apache-2.0). Changes from the base model are described under "How it was made".

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-1.7B
	datasets:
	- visproj/lantern-episodes
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- agents
	- tool-use
	- distillation
	- nethack
	- minihack
	---

	# Lantern-1.7B

	A 1.7B model that plays dungeon levels by calling tools, distilled from [Beam](https://huggingface.co/reflection/Beam-1.0-501B-A23B). It's the student half of [Lantern](https://huggingface.co/spaces/visproj/lantern).

	## How it was made

	- Base model: [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) (Apache-2.0).
	- Teacher: Beam 1.0 by Reflection (Apache-2.0). Beam's model card states that Reflection doesn't prohibit distillation or using its outputs to train other models.
	- Data: every Beam call from the winning episodes of the Lantern benchmark: 1,031 examples from 58 episodes across 8 MiniHack levels. Each example is the exact system prompt and observation Beam saw, and the tool calls it made (`act` with a list of moves, and `write_notes`). Only episodes with the current prompt version are used, and runs where a person coached the agent are left out. Data: [visproj/lantern-episodes](https://huggingface.co/datasets/visproj/lantern-episodes).
	- Training: supervised fine-tuning with TRL, loss on the completion only, 3 epochs, learning rate 1e-5 (cosine), effective batch size 16, bf16, on one A100. Final training loss 0.37. Qwen3's thinking mode is turned off: the student answers with a tool call directly, without Beam's reasoning.

	## Results

	Same 8 MiniHack levels × 5 seeds, same prompt and tools, no journal:

	\| Model \| Wins \|
	\|---\|---\|
	\| Beam 1.0 (501B, teacher) \| 23 / 40 \|
	\| Lantern-1.7B \| 11 / 40 \|
	\| Qwen3-1.7B, untrained \| 2 / 40 \|

	Per level, the student won Small Room 5/5, Room with Monsters 2/5, Memento 2/5, Key Room 1/5 and Corridors 1/5, and none of River Crossing, Maze Walk or Hide and Seek. Full per-level tables are in the [Space README](https://huggingface.co/spaces/visproj/lantern).

	## How to use it

	The model expects Lantern's prompt format and tool schema. Both are in the dataset: each episode's `start` event holds the exact system prompt and tool schema, and each `turn` event holds the observation prompt the model saw.

	Serve it with vLLM and send requests in that format, with thinking turned off:

	```bash
	vllm serve visproj/lantern-1.7b --enable-auto-tool-choice --tool-call-parser hermes
	```

	Pass `{"chat_template_kwargs": {"enable_thinking": false}}` in the request body. The model replies with `act` or `write_notes` tool calls.

	## Limitations

	- It learned only from Beam's wins, so it has seen far fewer examples of recovering from mistakes than of clean play.
	- It doesn't reason before acting the way Beam does, which matters most on the long levels.
	- It's trained on Lantern's exact observation format. Other prompts or games will need retraining.
	- 1,031 examples is a small dataset. Treat this as a proof of concept.

	## License

	Apache-2.0, as a fine-tune of Qwen3-1.7B (Apache-2.0). Changes from the base model are described under "How it was made".