GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AdarshSingh7647
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
AdarshSingh7647
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
Answer-only SFT is a lean baseline: the prompt carries no reasoning hint, and
the training target is just the bare verdict (true/false) with no
<think>...</think> chain-of-thought at all. It is trained on the full
(short) response with no loss masking, since there is nothing to mask.
This is not the same as the eklav-mask-only ablation, which keeps the
full reasoning trace in the response and masks it from the loss instead of
omitting it from the data. See
AdarshSingh7647/Eklav-Reranker-MaskOnly-Qwen3-8B
for that ablation.
AdarshSingh7647/Eklav-Reranker-AnswerOnly-Data
Final checkpoint, step 5968 (training complete).
LoRA adapter (PEFT format, r=32, alpha=64). Load with the base model:
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B")model = PeftModel.from_pretrained(base, "AdarshSingh7647/Eklav-Reranker-AnswerOnly-Qwen3-4B")tokenizer = AutoTokenizer.from_pretrained("AdarshSingh7647/Eklav-Reranker-AnswerOnly-Qwen3-4B")Part of the Eklav project.