Text Generation
PEFT
Safetensors
Nuosu
Chinese
English
qwen3
lora
nuosu
liangshan-yi
machine-translation
low-resource-language
academic-research
conversational
Instructions to use NiceAsiv/Qwen3-1.7B-Nuosu-MT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use NiceAsiv/Qwen3-1.7B-Nuosu-MT with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B") model = PeftModel.from_pretrained(base_model, "NiceAsiv/Qwen3-1.7B-Nuosu-MT") - Notebooks
- Google Colab
- Kaggle
| { | |
| "schema": "nuosu_model_release/1.0", | |
| "release": "qwen3-1.7b-nuosu-mt-v20260809", | |
| "base_model": "Qwen/Qwen3-1.7B", | |
| "base_revision": "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e", | |
| "training_code_revision": "90b7d6c3d71e025e1336a2a585389f1dedab9b6f", | |
| "chat_entrypoint_revision": "3c7f17f012e5a483c367ff7b5b16e905e1b2c7dd", | |
| "dataset_projection": "nuosu-mt-clean-recover-v20260808", | |
| "seed": 42, | |
| "training": { | |
| "train_records": 159083, | |
| "validation_records": 7131, | |
| "research_test_records": 8558, | |
| "epochs": 1, | |
| "dtype": "bfloat16", | |
| "lora_rank": 64, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0.05, | |
| "target_modules": "all-linear", | |
| "completion_only_loss": true | |
| }, | |
| "tokenizer": { | |
| "before_vocab_size": 151669, | |
| "after_vocab_size": 152872, | |
| "added_tokens": 1203, | |
| "added_tokens_sha256": "74930a7511a9e4d342b5c1c036196c0771701eac01f03be60683672bce318dac" | |
| }, | |
| "evaluation": { | |
| "full_exact_match": 0.036808, | |
| "full_compact_exact_match": 0.037626, | |
| "full_chrf2": 10.9349, | |
| "full_yi_exact_match": 0.025783, | |
| "gate_exact_match": 0.574219, | |
| "gate_chrf2": 60.6771, | |
| "gate_yi_exact_match": 0.484375, | |
| "gate_status": "waived_strict_gate_failure" | |
| }, | |
| "institution": "Xi'an Jiaotong University", | |
| "author": "Wuhe Axi" | |
| } | |