Support fine-tuning (#35)

- Support fine-tuning (1cad2ab3ff41c2671f34e135d29831368ee26b68)


Co-authored-by: tastelikefeet <tastelikefeet@users.noreply.huggingface.co>

README.md

@@ -5682,6 +5682,46 @@ In addition to the open-source [GTE](https://huggingface.co/collections/Alibaba-
 
 Note that the models behind the commercial APIs are not entirely identical to the open-source models.
 
+## Community support
+
+### Fine-tuning
+
+GTE models can be fine-tuned with a third party framework SWIFT.
+
+```shell
+pip install ms-swift -U
+```
+
+```shell
+# check: https://swift.readthedocs.io/en/latest/BestPractices/Embedding.html
+nproc_per_node=8
+NPROC_PER_NODE=$nproc_per_node \
+USE_HF=1 \
+swift sft \
+    --model Alibaba-NLP/gte-Qwen2-1.5B-instruct \
+    --train_type lora \
+    --dataset 'sentence-transformers/stsb' \
+    --torch_dtype bfloat16 \
+    --num_train_epochs 10 \
+    --per_device_train_batch_size 2 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps $(expr 64 / $nproc_per_node) \
+    --eval_steps 100 \
+    --save_steps 100 \
+    --eval_strategy steps \
+    --use_chat_template false \
+    --save_total_limit 5 \
+    --logging_steps 5 \
+    --output_dir output \
+    --warmup_ratio 0.05 \
+    --learning_rate 5e-6 \
+    --deepspeed zero3 \
+    --dataloader_num_workers 4 \
+    --task_type embedding \
+    --loss_type cosine_similarity \
+    --dataloader_drop_last true
+```
+
 ## Citation
 
 If you find our paper or models helpful, please consider cite: