GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CrowtherLabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CrowtherLabs
Model Tree
Input Modalities
Output Modalities
Supported Functionality
The model is a native vision-language model and loads through
AutoModelForImageTextToText.
python
import torchfrom transformers import AutoModelForImageTextToText, AutoTokenizerREPO = "CrowtherLabs/atom-proton-1.0"model = AutoModelForImageTextToText.from_pretrained(REPO,dtype=torch.bfloat16,device_map="auto",)model.eval()tokenizer = AutoTokenizer.from_pretrained(REPO)
Use AutoModelForCausalLM instead only if you intend to drop the vision tower and
serve the text-only decoder.
The weights occupy approximately 55 GB in bfloat16, so plan for an 80 GB
accelerator, or pass a quantization_config to fit a smaller one.
The architecture interleaves two attention types across its 64 layers, and the
linear-attention layers have a fast path that transformers does not ship. Without
it you will see
markdown
The fast path is not available ... Falling back to torch implementation
Serve this model at xhigh reasoning effort, which is the setting it was
adapted under. The chat template resolves effort as follows:
| value | effect on the system prefix |
|---|---|
| omitted | defaults to xhigh |
xhigh | full deliberation instruction |
high | alias for xhigh, identical output |
medium | no instruction line at all |
low | brief-thinking instruction |
Any other value raises an exception. Omitting the argument therefore gives the correct prefix already, but set it explicitly so that a client configured with a different default cannot silently change the prompt the model sees.
python
messages = [{"role": "system", "content": "You are Atom, one of Crowther's specialised AI models."},{"role": "user", "content": "Summarise the attached procurement policy in five points."},]text = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,reasoning_effort="xhigh", # must match the setting used in adaptation)inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=1024, do_sample=False)decoded = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
add_generation_prompt=True ends the prompt with <|im_start|>assistant\n<think>\n,
so generation begins inside the thinking block. The model emits its reasoning,
closes it with </think>, then writes the answer. Separate them on the closing
tag:
python
reasoning, _, answer = decoded.partition("</think>")
Show the answer to users, not the reasoning. Setting enable_thinking=False in
apply_chat_template suppresses reasoning, but the model was adapted exclusively
on thinking-enabled examples, so behaviour at that setting was not exercised.
The weights are a standard qwen3_5 architecture checkpoint, so any runtime with
support for that architecture can serve them:
bash
vllm serve CrowtherLabs/atom-proton-1.0 --dtype bfloat16
Pass the reasoning effort through the client's chat-template arguments so that the
system prefix matches adaptation. In an OpenAI-compatible request that is
chat_template_kwargs: {"reasoning_effort": "xhigh"}. Serving configuration was
not exercised during adaptation, so verify the rendered prompt before relying on
it in production.