GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
fotapol
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
fotapol
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-1.7B70d244cc86ccca08cf5af4e1e306ecf908b1ad5e6a89a40cb988567ee09e1ed049b19f09456ec84975738da9edec27613627b2e2The adapter is not merged into the base model. adapter_config.json records the exact base revision.
The schema-v6 training split contains 9,000 RAG-shaped chat examples:
Training used one epoch of 4-bit NF4 QLoRA on two NVIDIA T4 GPUs, LoRA rank 16, alpha 32, dropout 0.05, an effective batch size of 8, and a learning rate of 1e-4. All 1,125 optimizer steps completed. See training_metadata.json and dataset_manifest.json for reproducibility details.
On the complete 900-example schema-v6 validation split, using the same deterministic prompts for base and adapter:
| Metric | Base | v4 |
|---|---|---|
| Overall accuracy | 38.44% | 55.22% |
| Value accuracy | 41.25% | 55.42% |
| Unit accuracy | 41.94% | 91.00% |
| Citation completion | 33.33% | 83.47% |
| Calculation format | 0.00% | 90.83% |
| False-refusal rate | 41.39% |
Table-lookup overall accuracy improved from 60.13% to 98.73%. Across all examples, v4 improved 205 cases and regressed 54 relative to base.
A four-question frozen-context smoke test using financial_report_chunking_test.pdf passed 4/4 cases for direct lookup, large-table lookup, arithmetic reasoning, and an unsupported CEO question. Two contexts in this small diagnostic suite were oracle-augmented, so it is a generator smoke test rather than a complete end-to-end retrieval benchmark.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase_id = "Qwen/Qwen3-1.7B"base_revision = "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e"adapter_id = "fotapol/qwen3-1.7b-financial-rag-lora-v4"tokenizer = AutoTokenizer.from_pretrained(adapter_id)base = AutoModelForCausalLM.from_pretrained(base_id,revision=base_revision,device_map="auto",dtype="auto",)model = PeftModel.from_pretrained(base, adapter_id, is_trainable=False)model.eval()
Use the Qwen chat template with thinking disabled and deterministic decoding (do_sample=False). Supply retrieved context containing stable source labels such as [Source 1] and instruct the model to use only that context.
| 4.44% |
| Unsupported refusal accuracy | 86.67% | 65.56% |