GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sinhal
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
sinhal
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
| Rows seen | 6,714 (the whole dataset less the holdout; 5,000 were planned) |
| Sessions | 1 |
| Final training loss | 0.1456 |
| Method | QLoRA, 4-bit NF4, r=16, alpha=32 |
| Hardware | Kaggle T4 (16GB), free tier |
On 200 rows held out of training and never seen by the model, mean token loss fell from 2.3668 to 0.1418 (94.0% lower). The same rows were scored before and after training, so this is a like-for-like comparison rather than a training-loss curve.
| Held-out loss, base model | 2.3668 |
| Held-out loss, this adapter | 0.1418 |
| Loss reduction | 2.2250 (94.0% lower) |
| Held-out rows | 200 |
Trained in 1 session on Kaggle's free GPU, which stops at twelve hours - longer runs resume from the previous session's checkpoint.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")model = PeftModel.from_pretrained(base, "sinhal/qwen3-4b-instruct-2507-gsm8k-reasoning")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
Trained on one dataset for 1 session on free-tier hardware. It has not been benchmarked, and no claim is made that it beats the base model at anything. It exists because the pipeline that produced it runs unattended, and it is published so the work is inspectable.
Built and published automatically by an agent. The base model and dataset licences above govern use.