Instructions to use Remek/basal-2.0-max with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Remek/basal-2.0-max with Transformers:

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

pipe = pipeline("text-generation", model="Remek/basal-2.0-max")
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("Remek/basal-2.0-max")
model = AutoModelForCausalLM.from_pretrained("Remek/basal-2.0-max", 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 Remek/basal-2.0-max with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Remek/basal-2.0-max"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Remek/basal-2.0-max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Remek/basal-2.0-max

SGLang

How to use Remek/basal-2.0-max 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 "Remek/basal-2.0-max" \
    --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": "Remek/basal-2.0-max",
		"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 "Remek/basal-2.0-max" \
        --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": "Remek/basal-2.0-max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Remek/basal-2.0-max with Docker Model Runner:
```
docker model run hf.co/Remek/basal-2.0-max
```

Remek commited on 17 days ago

Commit

2fffc5c

verified ·

1 Parent(s): 73e8425

docs: list the tool question type in the model card

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ tags:
 **basal-2.0-max** is part of basal-2.0, a family of typed-decision models for Polish and English; it is the most accurate model of the family. Built on Bielik-PL-11B-v3.0-Instruct. Trained further from earlier basal checkpoints.
 **What it is.** The model reads a *state* (a message, a document, retrieved passages, an agent trace, a web page as
-JSON) and answers a typed question about it (`choice`, yes/no `noul`, `score`, `multi`, `act`) by returning a
 **calibrated probability for each allowed answer**, in one forward pass, without generating text. The answer never falls
 outside the options you give, and the probability says how sure the model is. Because the classes are described in the
 request, one model serves many tasks without retraining: routing, rule and policy checks, questions about long
@@ -42,7 +42,7 @@ Each model also comes as `-FP8` (NVIDIA Hopper and Blackwell), `-GGUF` (Q8_0 and
 - **Good for:** routing messages and documents to one of the options you describe; yes/no checks of rules and policies;
   urgency and risk scores; questions about long documents and retrieved passages (is the answer there, is it relevant);
-  judging answers; choosing an agent's next action or tool; triage that hands uncertain cases to a person (an `act`
   question with a defer action and `max_error`).
 - **Languages:** Polish and English (the state and the question may be in either).
 - **Not for:** writing text or chatting (the model only picks among the options you give); facts that are not in the

 **basal-2.0-max** is part of basal-2.0, a family of typed-decision models for Polish and English; it is the most accurate model of the family. Built on Bielik-PL-11B-v3.0-Instruct. Trained further from earlier basal checkpoints.
 **What it is.** The model reads a *state* (a message, a document, retrieved passages, an agent trace, a web page as
+JSON) and answers a typed question about it (`choice`, yes/no `noul`, `score`, `multi`, `act`, `tool`) by returning a
 **calibrated probability for each allowed answer**, in one forward pass, without generating text. The answer never falls
 outside the options you give, and the probability says how sure the model is. Because the classes are described in the
 request, one model serves many tasks without retraining: routing, rule and policy checks, questions about long
 - **Good for:** routing messages and documents to one of the options you describe; yes/no checks of rules and policies;
   urgency and risk scores; questions about long documents and retrieved passages (is the answer there, is it relevant);
+  judging answers; choosing an agent's next action or tool (a `tool` question over OpenAI or MCP tool definitions picks the tool, not its arguments); triage that hands uncertain cases to a person (an `act`
   question with a defer action and `max_error`).
 - **Languages:** Polish and English (the state and the question may be in either).
 - **Not for:** writing text or chatting (the model only picks among the options you give); facts that are not in the