GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
modrill
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
modrill
Model Tree
Qwen/Qwen3-4B-Base
Input Modalities
Output Modalities
Supported Functionality
PEFT LoRA adapter trained on a frozen CN11 equal-update recipe:
| Field | Value |
|---|---|
| Base | Qwen/Qwen3-4B-Base |
| Base revision | 906bfd4b4dc7f14ee4320094d8b41684abff8539 |
| Recipe | FC250 + COT250 (token-balanced) |
LoRA rank r / U | 64 |
lora_alpha | 128 |
lora_dropout | 0.0 |
| Cutoff | 4096 |
| Rows | 1074 (FC 923 + COT 151) |
| Supervised target tokens | 500,000 non-padding unique |
| Train seed | 43 |
| Optimizer steps | 64 |
| Fresh LoRA from base | yes |
Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj.
Published adapter_config.json rewrites only base_model_name_or_path from a local snapshot path to Qwen/Qwen3-4B-Base so PEFT can resolve the public base. Adapter weights (adapter_model.safetensors) are an exact copy of the frozen COMPLETE artifact.
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase_id = "Qwen/Qwen3-4B-Base"base_rev = "906bfd4b4dc7f14ee4320094d8b41684abff8539"adapter_id = "modrill/CN11-OCR-FC250-COT250-U64"tokenizer = AutoTokenizer.from_pretrained(base_id, revision=base_rev)model = AutoModelForCausalLM.from_pretrained(base_id,revision=base_rev,torch_dtype=torch.bfloat16,device_map="auto",)model = PeftModel.from_pretrained(model, adapter_id)model.eval()
AutoPeftModelForCausalLM.from_pretrained("modrill/CN11-OCR-FC250-COT250-U64") should also work after the published config rewrite. Always pin the base revision above.
Public full-LCB latest, 1055 tasks, pass@1. Two separate seed groups. Do not average them into one score.
0.2581358609794629)0.24739336492890995)+0.010742496050552922)[-0.0006319115323854657, 0.022116903633491312] — crosses zero0.24486571879936808)+0.002211690363349131)[-0.01042654028436019, 0.014533965244865717] — crosses zeroBoth results are DIAGNOSTIC_ONLY. Confidence intervals cross zero. This adapter is NOT_WINNER.
Adapter weights follow the base model license: Apache 2.0 (Qwen/Qwen3-4B-Base).