GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mundetr1
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mundetr1
Model Tree
Qwen/Qwen3-0.6B-Base
Input Modalities
Output Modalities
Supported Functionality
Research on prompt-fact retrieval, multi-step program control and premature stopping. It is a Base-derived formal-task model, not a conversational assistant. Load it without a chat template or remote code. Its failures on longer programs are part of the research, rather than a solved capability.
da87bfb608c14b7cf20ba1ce41287e8de496c0cd.Training targets count supervised trace tokens, not all prompt tokens. Qwen pretraining is inherited; see the upstream model card.
The archived native benchmark contains 2,560 complete greedy traces, 40 per depth/family cell across depths 1–16 and four alternating/repeated relation families. Within trained depths 1–10, exact accuracy is 1,548/1,600 (96.8%). Beyond them, it is 128/960 (13.3%). Of 832 extrapolation errors, 823 (98.9%) first fail by premature DONE, four by a wrong result and five by unnecessary continuation. These are archived results for one checkpoint and specified panels, not a new replication or a general reasoning benchmark.
In one actual depth-12 repeated-IN trace, the model returns OSCAR16 correctly at turn 10 but announces DONE. It omits the last two lookups. The stopping algorithm remains unresolved. Copying tested late object-token keys and values can transfer an answer, and a block-11 direction can rescue individual action fields; neither finding establishes a complete circuit or safe autonomous execution.
bash
python -m pip install "huggingface-hub==0.35.3" "transformers==4.57.1" "torch==2.7.1" "safetensors==0.6.2"hf download mundetr1/where-is-shakespeare-final-d --revision final-d-v1 --local-dir models/final-dChoose an appropriate CUDA build of torch for GPU use. The three safetensors shards total about 2.4 GB. MANIFEST.json gives exact byte counts and SHA-256 hashes for every weight, tokenizer, configuration and license file.
python
import hashlibimport jsonfrom pathlib import Path root = Path("models/final-d")manifest = json.loads((root / "MANIFEST.json").read_text())for name, expected in manifest["files"].items(): h = hashlib.sha256() with (root / name).open("rb") as stream: for chunk in iter(lambda: stream.read(8 * 1024 * 1024), b""): h.update(chunk) assert (root / name).stat().st_size == expected["bytes"], name assert h.hexdigest() == expected["sha256"], nameprint("MODEL_CHECKSUMS_PASS")This cleaned symbolic example teaches the task; it is not a newly measured model result. Real prompts also contain distractor facts. Read the nested query from the inside out. Each line returns a result and announces the next operation; depth four means four lookups and four lines, including the final DONE line.
text
NORA16 -> JACK20 | JACK20 IN NORA17 | NORA17 -> ALICE23 | ALICE23 IN ALICE19 | ?IN ?-> ?IN ?-> NORA16 |Expected oracle trace:
text
JACK20 | INNORA17 | ->ALICE23 | INALICE19 | DONEpython
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer path = "models/final-d"device = "cuda" if torch.cuda.is_available() else "cpu"torch.backends.cuda.matmul.allow_tf32 = Falsetorch.backends.cudnn.allow_tf32 = Falsetokenizer = AutoTokenizer.from_pretrained(path, local_files_only=True, trust_remote_code=False)model = AutoModelForCausalLM.from_pretrained( path, local_files_only=True, trust_remote_code=False, torch_dtype=torch.float32, attn_implementation="sdpa",).to(device).eval()prompt = 'NORA16 -> JACK20 | JACK20 IN NORA17 | NORA17 -> ALICE23 | ALICE23 IN ALICE19 | ?IN ?-> ?IN ?-> NORA16 |'inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(device)with torch.inference_mode(): output = model.generate(**inputs, do_sample=False, max_new_tokens=128, pad_token_id=tokenizer.eos_token_id)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))CPU inference is possible but slower. Scientific interventions used FP32 with TF32 disabled and a numerical-equivalence gate. Basic generation above is a usage example, not that full gate or causal assay. Exact outputs can depend on the implementation and numerical environment.
Longer programs often stop early. Other assays can produce overruns and malformed traces. A successful intervention on one field can harm complete execution. The model is not a general reliable controller, and these results cover one seed and checkpoint. The complete minimal retrieval circuit and definitive stop rule remain open. No new training or GPU scientific campaign was run to publish this package. Cite the model repository and exact revision or tag used in your work.
The associated research repository is currently private: Where-is-Shakespeare. Model access here is public and independent of access to that code repository.
python -m pip install "huggingface-hub==0.35.3" "transformers==4.57.1" "torch==2.7.1" "safetensors==0.6.2"hf download mundetr1/where-is-shakespeare-final-d --revision final-d-v1 --local-dir models/final-dimport hashlibimport jsonfrom pathlib import Path root = Path("models/final-d")manifest = json.loads((root / "MANIFEST.json").read_text())for name, expected in manifest["files"].items(): h = hashlib.sha256() with (root / name).open("rb") as stream: for chunk in iter(lambda: stream.read(8 * 1024 * 1024), b""): h.update(chunk) assert (root / name).stat().st_size == expected["bytes"], name assert h.hexdigest() == expected["sha256"], nameprint("MODEL_CHECKSUMS_PASS")JACK20 | INNORA17 | ->ALICE23 | INALICE19 | DONEimport torchfrom transformers import AutoModelForCausalLM, AutoTokenizer path = "models/final-d"device = "cuda" if torch.cuda.is_available() else "cpu"torch.backends.cuda.matmul.allow_tf32 = Falsetorch.backends.cudnn.allow_tf32 = Falsetokenizer = AutoTokenizer.from_pretrained(path, local_files_only=True, trust_remote_code=False)model = AutoModelForCausalLM.from_pretrained( path, local_files_only=True, trust_remote_code=False, torch_dtype=torch.float32, attn_implementation="sdpa",).to(device).eval()prompt = 'NORA16 -> JACK20 | JACK20 IN NORA17 | NORA17 -> ALICE23 | ALICE23 IN ALICE19 | ?IN ?-> ?IN ?-> NORA16 |'inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(device)with torch.inference_mode(): output = model.generate(**inputs, do_sample=False, max_new_tokens=128, pad_token_id=tokenizer.eos_token_id)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))