GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
physicsrob
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
physicsrob
Model Tree
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForCausalLM, AutoTokenizerrepo_id = 'physicsrob/torchwright-calculator-advanced-max-digits-6'model = AutoModelForCausalLM.from_pretrained(repo_id).eval()tok = AutoTokenizer.from_pretrained(repo_id)enc = tok('12*34\n', return_tensors="pt")out = model.generate(enc["input_ids"], max_new_tokens=32, do_sample=False,eos_token_id=tok.eos_token_id, pad_token_id=tok.eos_token_id)print(tok.decode(out[0, enc["input_ids"].shape[1]:], skip_special_tokens=True))
Prompts are A op B terminated by a newline: two non-negative decimal
operands of up to 6 digits, with op one of +, -, *.
Subtraction may produce a negative result. Wider operands, or any character
outside the model's small vocabulary, are outside the contract — the output
is undefined.
| prompt | output |
|---|---|
12*34 | 408 |
7+8 | 15 |
999999*999999 | 999998000001 |
999999+1 | 1000000 |
999999-123456 | 876543 |
123456-999999 | -876543 |
This model is a demonstration of a computation graph compiled into transformer weights. It is not a general language model or a general-purpose calculator; only the input contract above is supported.
The examples above are exact reference outputs. The Modal publishing path
reloads the emitted checkpoint through stock transformers, checks those
examples plus additional width-limit cases against Python integer arithmetic,
and refuses to upload on a mismatch. This is a functional smoke test, not
exhaustive verification of every allowed expression.
The checkpoint stores 59.14 GB of dense fp32 weights (14,785,806,336 entries) at the example family's shared compile width. 100.00% of those entries are exactly zero: the vast majority of the model is unused canvas, so size reflects the compile geometry rather than stored knowledge.
The zero entries are not compressed, and dense transformers execution still
pays their memory and compute cost. CPU execution is supported; allow
additional RAM beyond the checkpoint size.
One example of many compiled with torchwright. Calculator siblings —
calculator-simple (serial arithmetic, depth grows with the digit count),
calculator-advanced (carry-lookahead, near-flat depth),
calculator-scratchpad (flat depth; the serial work streams out as visible
thinking tokens), and calculator-memorize (no arithmetic at all: a fact
table, exponential in the digit count) — are published at several digit
widths. Browse the
torchwright calculator models
on Hugging Face.