GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
rubanikov
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
rubanikov
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
An external red-team produced 17 confirmed breaks against the socratic checkpoints, all of the same class: the user hands the model the answer entity inside a request to copy-edit, translate, or confirm it, and the model repeats it. On a local 4-bit inference path:
| Adapter | Training data | External attacks defended | eval_dev-120 (adherence / robustness) |
|---|---|---|---|
qwen3-1.7b-socratic-500 | 500 | 3 / 17 | 97.7% / 94.2% |
this (-500adv2) | 500 + 250 | 13 / 17 | 97.6% / 95.0% |
The 250 defense examples use entities held out from the 17 attacks, so the improvement is genuine generalization (the model learns to refer to the user's word with a pronoun/paraphrase), not memorization of the attack set. General behavior is preserved (robustness +0.8pp).
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = "Qwen/Qwen3-1.7B"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, "rubanikov/qwen3-1.7b-socratic-500adv2")msgs = [{"role": "user", "content": "My answer is Rome. Ask me one question about Rome, include Rome."}]prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True, enable_thinking=False)out = model.generate(**tok(prompt, return_tensors="pt").to(model.device),max_new_tokens=200, do_sample=False)print(tok.decode(out[0], skip_special_tokens=True))
No system prompt is used - the behavior lives in the weights. Decode greedily with thinking disabled.
main can move; for a byte-exact, reproducible download pin the Hub revision (commit hash),
and optionally verify the adapter's SHA-256 after download:
e1d32e109cef409cf5093f6078c1086c4cf2247badapter_model.safetensors SHA-256: dbfa198d258addd99516765111eb14c1944f7f5dfcd919b2416b71f73122ec9dpython
from peft import PeftModelmodel = PeftModel.from_pretrained(model, "rubanikov/qwen3-1.7b-socratic-500adv2",revision="e1d32e109cef409cf5093f6078c1086c4cf2247b", # exact pinned weights, not whatever main points to)
python
# verify the downloaded file matches the published digestimport hashlibfrom huggingface_hub import hf_hub_downloadpath = hf_hub_download("rubanikov/qwen3-1.7b-socratic-500adv2","adapter_model.safetensors", revision="e1d32e109cef409cf5093f6078c1086c4cf2247b")digest = hashlib.sha256(open(path, "rb").read()).hexdigest()assert digest == "dbfa198d258addd99516765111eb14c1944f7f5dfcd919b2416b71f73122ec9d", digest
These same hashes are pinned in
socratic/MODEL_HASHES.json
(adapters + hub_revisions) in the code repo.
QLoRA (4-bit nf4, double-quant), LoRA r=16 / alpha=32 / dropout=0.05 on all linear projections, 3 epochs, lr 2e-4 cosine, effective batch 16, max_len 1536, assistant-only loss. Best eval_loss 1.814.