Instructions to use theostos/qwen-3.5-babel-2b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theostos/qwen-3.5-babel-2b-sft with Transformers:

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

pipe = pipeline("text-generation", model="theostos/qwen-3.5-babel-2b-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("theostos/qwen-3.5-babel-2b-sft")
model = AutoModelForCausalLM.from_pretrained("theostos/qwen-3.5-babel-2b-sft", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use theostos/qwen-3.5-babel-2b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theostos/qwen-3.5-babel-2b-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theostos/qwen-3.5-babel-2b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/theostos/qwen-3.5-babel-2b-sft

SGLang

How to use theostos/qwen-3.5-babel-2b-sft 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 "theostos/qwen-3.5-babel-2b-sft" \
    --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": "theostos/qwen-3.5-babel-2b-sft",
		"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 "theostos/qwen-3.5-babel-2b-sft" \
        --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": "theostos/qwen-3.5-babel-2b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use theostos/qwen-3.5-babel-2b-sft with Docker Model Runner:
```
docker model run hf.co/theostos/qwen-3.5-babel-2b-sft
```

qwen-3.5-babel-2b-sft

This is the 2B supervised-fine-tuned checkpoint from Babel-Formal, a research project on proof-term-to-tactic-script translation between Lean and Rocq.

The checkpoint is derived from Qwen/Qwen3.5-2B and fine-tuned on the Babel Lean/Rocq term-to-script training corpus. It is released as a text-only Qwen3_5ForCausalLM checkpoint: the original Qwen3.5 wrapper's language-model parameters and tokenizer are retained, while no vision encoder weights are included.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "theostos/qwen-3.5-babel-2b-sft"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

Use the prompting and verification pipeline in the Babel-Formal repository for Lean/Rocq translation experiments. Generated proof scripts must be checked by the target prover; the model does not guarantee correctness.

Limitations

This is a research checkpoint specialized for formal-proof translation.
It is not a general-purpose mathematical correctness oracle.
Outputs can be syntactically invalid or fail verification.
The model card does not claim that pretraining-data contamination has been excluded.

License

Apache 2.0, following the upstream Qwen3.5 checkpoint.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for theostos/qwen-3.5-babel-2b-sft

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

(385)

this model