GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. 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
Base
Qwen/Qwen3-4B-Base
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
| Field | Value |
|---|---|
| Epochs | 2 |
| Seed | 42 |
| cutoff_len | 24576 |
| packing | true |
| neat_packing | false |
| per_device_train_batch_size | 1 |
| gradient_accumulation_steps | 16 |
| effective_batch_size | 64 |
| learning_rate | 5e-5 |
| train_loss | 0.5416 |
| train_steps | 604 |
| finished_at | 2026-06-10 05:23 CST |
Optimizer: AdamW (fused), cosine schedule, warmup ratio 0.1. Framework: Transformers 5.6.0, PyTorch 2.8.0+cu128.
python
from transformers import AutoModelForCausalLM, AutoTokenizerrepo_id = "modrill/qwen3-4b-think-s1-ep23-full-sft"tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(repo_id,torch_dtype="auto",device_map="auto",trust_remote_code=True,)
Released under Apache 2.0 (see LICENSE in the upstream Qwen model card if not bundled here).