GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ichetandhembre
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
ichetandhembre
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
Greedy exact-match on a 5,914-row held-out split (provably disjoint from training by input):
| Model | Exact-match | Relaxed-match | mean_reward* |
|---|---|---|---|
| Base Qwen3-4B-Instruct-2507 | 0.409 | 0.577 | 0.472 |
| This adapter (SFT) | 0.932 | 0.976 | 0.939 |
*mean_reward is the normalized reward (exact·1.0 + pii_count·0.5 + format·0.1) / 1.6 (max 1.0).
The Prime Intellect verifier for this task reports the same three components un-normalized
(max 1.6), so e.g. a Prime reward of ~1.50 corresponds to ~0.94 here.
Format compliance is already ~1.00 on the base model; the adapter's gain is almost entirely
learning the exact [PII] segmentation convention (it cuts the relaxed-minus-exact gap from
0.168 to 0.045).
AdamLucek/open-pii-masking-en-us-30k (train split).The published adapter was extracted from the merged SFT checkpoint by a per-layer rank-8 SVD of
(W_merged − W_base). Base + this adapter reproduces the merged model's held-out exact-match to
within bf16 rounding (0.9319 vs 0.9325).
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507", torch_dtype="bfloat16", device_map="auto")model = PeftModel.from_pretrained(base, "ichetandhembre/Qwen3-4B-Instruct-2507-PII-SFT-LoRA")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")SYSTEM = ("Replace all personally identifiable information (PII) in the text with [PII] tags. ""PII includes: names, dates, phone numbers, SSNs, account numbers, addresses, ""email addresses. Wrap the masked text in <masked_output>...</masked_output>.")msgs = [{"role": "system", "content": SYSTEM},{"role": "user", "content": "Hi, this is John Smith, call me at 555-0123."}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)print(tok.decode(model.generate(ids, max_new_tokens=384, do_sample=False)[0][ids.shape[1]:],skip_special_tokens=True))
Or serve base + adapter with vLLM (enable_lora=True, max_lora_rank>=8).