Update README.md

README.md

@@ -1,6 +1,5 @@
 ---
 license: apache-2.0
----
 datasets:
 - huihui-ai/QWQ-LONGCOT-500K
 - huihui-ai/LONGCOT-Refine-500K
@@ -20,7 +19,8 @@ The model was trained using 1 RTX 4090 GPU(24GB)
 The [SFT (Supervised Fine-Tuning)](https://github.com/modelscope/ms-swift) process is divided into several steps, and no code needs to be written.
 1. Create the environment.
 
-'''
+```
+
 mkdir MicroThinker-1B-Preview
 cd MicroThinker-1B-Preview
 conda create -yn ms-swift python=3.11
@@ -31,48 +31,69 @@ git clone https://github.com/modelscope/ms-swift.git
 cd ms-swift
 pip install -e .
 cd ..
-'''
+```
+
 
 2. Download the model and dataset.
 
-'''
+```
+
 huggingface-cli download huihui-ai/Llama-3.2-1B-Instruct-abliterated --local-dir ./huihui-ai/Llama-3.2-1B-Instruct-abliterated
 huggingface-cli download --repo-type  dataset huihui-ai/QWQ-LONGCOT-500K --local-dir ./data/QWQ-LONGCOT-500K
 huggingface-cli download --repo-type  dataset huihui-ai/LONGCOT-Refine-500K --local-dir ./data/LONGCOT-Refine-500K
-'''
+```
+
 
 3. Used only the huihui-ai/QWQ-LONGCOT-500K dataset (#20000), Trained for 1 epoch:
 
-'''
+```
+
 swift sft --model huihui-ai/Llama-3.2-1B-Instruct-abliterated --model_type llama3_2 --train_type lora --dataset "data/qwq_500k.jsonl#20000" --torch_dtype bfloat16 --num_train_epochs 1 --per_device_train_batch_size 1 --per_device_eval_batch_size 1 --learning_rate 1e-4 --lora_rank 8 --lora_alpha 32 --target_modules all-linear --gradient_accumulation_steps 16 --eval_steps 50 --save_steps 50 --save_total_limit 2 --logging_steps 5  --max_length 16384  --output_dir output/Llama-3.2-1B-Instruct-abliterated/lora/sft --system "You are a helpful assistant. You should think step-by-step." --warmup_ratio 0.05 --dataloader_num_workers 4 --model_author "huihui-ai" --model_name "huihui-ai-robot"
-'''
+```
+
 
 4. Save the fine-tuned model.
 Replace the directories below with specific ones.
 
-'''
+```
+
 swift infer --model huihui-ai/Llama-3.2-1B-Instruct-abliterated --adapters output/Llama-3.2-1B-Instruct-abliterated/lora/sft/v0-20250102-153619/checkpoint-1237 --merge_lora true 
-'''
+```
+
 
 This should create a new model directory: `checkpoint-1237-merged`, Copy or move this directory to the `huihui` directory.
 
+5. Perform inference on the fine-tuned model.
+
+```
+
+swift infer --model huihui/checkpoint-1237-merged --stream true --infer_backend pt --max_new_tokens 8192
+```
+
+
 5. Combined training with huihui-ai/QWQ-LONGCOT-500K (#20000) and huihui-ai/LONGCOT-Refine datasets (#20000), Trained for 1 epoch:
 
-'''
+```
+
 swift sft --model huihui-ai/checkpoint-1237-merged --model_type llama3_2 --train_type lora --dataset "data/qwq_500k.jsonl#20000" "data/refine_from_qwen2_5.jsonl#20000" --torch_dtype bfloat16 --num_train_epochs 1 --per_device_train_batch_size 1 --per_device_eval_batch_size 1 --learning_rate 1e-4 --lora_rank 8 --lora_alpha 32 --target_modules all-linear --gradient_accumulation_steps 16 --eval_steps 50 --save_steps 50 --save_total_limit 2 --logging_steps 5  --max_length 16384  --output_dir output/Llama-3.2-1B-Instruct-abliterated/lora/sft2 --system "You are a helpful assistant. You should think step-by-step." --warmup_ratio 0.05 --dataloader_num_workers 4 --model_author "huihui-ai" --model_name "huihui-ai-robot"
-'''
+```
+
 
 6. Save the final fine-tuned model.
 Replace the directories below with specific ones.
 
-'''
+```
+
 swift infer --model huihui-ai/checkpoint-1237-merged --adapters output/Llama-3.2-1B-Instruct-abliterated/lora/sft2/v0-20250103-121319/checkpoint-1237 --merge_lora true 
-'''
+```
+
 
 This should create a new model directory: `checkpoint-1237-merged`, Rename the directory to `MicroThinker-1B-Preview`, Copy or move this directory to the `huihui` directory.
 
 7. Perform inference on the final fine-tuned model.
 
-'''
+```
+
 swift infer --model huihui/MicroThinker-1B-Preview --stream true --infer_backend pt --max_new_tokens 8192
-'''
+```
+