Instructions to use webbrain-one/webbrain-compass-tiny-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webbrain-one/webbrain-compass-tiny-v2 with Transformers:

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

pipe = pipeline("text-generation", model="webbrain-one/webbrain-compass-tiny-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webbrain-one/webbrain-compass-tiny-v2")
model = AutoModelForCausalLM.from_pretrained("webbrain-one/webbrain-compass-tiny-v2", 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 webbrain-one/webbrain-compass-tiny-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webbrain-one/webbrain-compass-tiny-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webbrain-one/webbrain-compass-tiny-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/webbrain-one/webbrain-compass-tiny-v2

SGLang

How to use webbrain-one/webbrain-compass-tiny-v2 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 "webbrain-one/webbrain-compass-tiny-v2" \
    --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": "webbrain-one/webbrain-compass-tiny-v2",
		"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 "webbrain-one/webbrain-compass-tiny-v2" \
        --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": "webbrain-one/webbrain-compass-tiny-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use webbrain-one/webbrain-compass-tiny-v2 with Docker Model Runner:
```
docker model run hf.co/webbrain-one/webbrain-compass-tiny-v2
```

webbrain-compass-tiny-v2 / README.md

webbrain-one

Correct release name to WebBrain Compass Tiny v2

54bcab6 verified 15 days ago

preview code

Raw

History Blame Contribute Delete

5.77 kB

	---
	license: other
	license_name: webbrain-noncommercial-research-restrictions
	license_link: https://huggingface.co/webbrain-one/webbrain-compass-tiny-v2/blob/main/ATTRIBUTIONS.md
	library_name: transformers
	base_model: openbmb/MiniCPM5-2B
	tags:
	- experimental
	- web-agent
	- tool-calling
	- lora-merged
	- bf16
	---
	# WebBrain Compass Tiny v2 — experimental private BF16

	Release naming correction: formerly `webbrain-compass-v2`. Model weights,
	tokenizer, configuration and benchmark results are unchanged. Historical
	run IDs and provenance retain their original names for reproducibility.

	Full merged model weights, not an adapter. This experimental release was
	explicitly authorized after disclosure of a failed behavioral gate. It is NOT
	a release that passed every v4 gate. Do not deploy unattended browser actions
	on the strength of these small-suite results.

	## Training and representation

	Base: OpenBMB MiniCPM5-2B, revision
	`3497c460c89e00520c3cfa2e73f49ab7647f1177`. One epoch, 7,311 training examples,
	213 validation examples, 457 optimizer steps. LoRA r16/alpha32 deltas were
	accumulated in FP32 and parameters cast once to BF16. Native nonpersistent
	rotary-position buffers remain FP32, as in stock Transformers loading.
	No optimizer, RNG state or training examples are included here.

	## Candidate-specific evaluation

	\| Metric \| This merged BF16 \| Native adapter \| Historical Qwen3.8-27B \|
	\|---\|---:\|---:\|---:\|
	\| Structured first turn \| 94/100 \| 93/100 \| 99/100 \|
	\| Strict tool and arguments \| 16/89 \| 15/89 \| 17/89 \|
	\| Loose tool/name credit \| 41/89 (46.1%) \| 43/89 (48.3%) \| 39/89 (43.8%) \|

	Eleven out-of-scope cases are skipped; all other cases, including technical
	errors, stay in the 89-case denominator. This BF16 run had one known
	anti-pattern, zero HTTP/runner errors or timeouts, and **one malformed XML
	response**. The parse failure was not repaired or regraded. The native-adapter
	run had one timeout, retained in its score.

	Failed v4 gate: loose >=43/89; observed 41/89. Other aggregate v4 gates
	passed. The user accepted an experimental/private distribution with this
	limitation disclosed; neither the failed gate nor the original evidence was
	changed. This is separate from numerical weight/reload verification.

	All 193 frozen input/code hashes and scenario references match between the
	native-adapter and merged-BF16 runs. GPU: RTX 5090; thinking disabled; seed 3407;
	action temperature 0.15, Ask temperature 0.3. No selective retries. These tests
	predict the next response; browser actions were not executed, so this is
	not end-to-end task success, general capability equivalence or a safety claim.

	Qwen figures are historical results from the
	[public routing comparison](https://www.webbrain.one/blog/compact-tool-routing-models-compared).
	Historical/current byte-identical prompts and tools have not been established.
	The small differences do not establish statistical superiority or parity with
	Qwen's broader capabilities. These are not controlled speed comparisons.

	## Numerical validation and preserved failures

	All 294 adapted weight deltas were independently checked against the pinned
	raw base and adapter, with unchanged unadapted weights and finite parameters.
	Eight frozen calibration probes passed FP32 merged/unmerged comparisons
	(maximum absolute logit error <=0.001, relative L2 <=0.0001, identical greedy
	tokens). The saved/reloaded BF16 weight bits, config, tokenizer and template
	match; all eight reload logit comparisons had zero error, and corresponding
	KV-cache decode outputs matched.

	This is not numerically identical to unmerged BF16 inference. Earlier v1/v2
	absolute-logit parity gates failed and remain failed. An earlier v4 reload
	comparison also failed after whole-module casting rounded nonpersistent RoPE
	buffers. An independent diagnostic reproduced that discrepancy exactly by
	changing only those buffers. The frozen v4.2 source casts parameters only and
	preserves FP32 runtime buffers; stored model weight bits are unchanged from
	the earlier v4 candidate. A v4.1 startup attempt failed before inference due
	to Windows source-decoding differences; explicit UTF-8 restored exact frozen
	inputs. None of these failures was deleted or relabeled as a pass.

	## Native inference interface

	Verified runtime: Transformers 5.16.1, PyTorch 2.13.0+cu130, stock
	`LlamaForCausalLM`, with the included tokenizer and chat template. Load with
	`dtype=torch.bfloat16`; do not cast the whole module afterward, which can
	round native FP32 runtime buffers.

	Use `enable_thinking=False` and `add_generation_prompt=True`. Tool-call
	arguments in conversation history must be dictionaries, not JSON strings.
	Output uses native XML, for example
	`<function name="..."><param name="...">...</param></function>`.
	Do not decode using `skip_special_tokens=True`: it removes tool delimiters.
	Remove only terminal EOS token IDs 1 or 130073. Preserve raw outputs and parse
	complete XML; fail closed on malformed output without repairing arguments.

	## Access, attribution and restrictions

	Private, experimental, noncommercial/research-only under project policy.
	The training package includes WebLINX (CC BY-NC-SA 4.0); preserve attribution,
	applicable share-alike requirements and all dataset source obligations.
	The base model is Apache-2.0. Private hosting is not permission for commercial
	use. See ATTRIBUTIONS.md and LICENSE-BASE-APACHE-2.0.txt.

	The associated dataset is
	[private](https://huggingface.co/datasets/webbrain-one/webbrain-compass-v2-dataset).
	Release provenance, original failed-gate audit, numerical verification and
	explicit experimental authorization are in `provenance/`.
	ONNX requires separate export/runtime verification; these BF16 results must
	not be claimed as measured ONNX results.