Update README.md

README.md

@@ -1,3 +1,105 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+datasets:
+- huihui-ai/QWQ-LONGCOT-500K
+- huihui-ai/LONGCOT-Refine-500K
+base_model:
+- huihui-ai/Llama-3.2-3B-Instruct-abliterated
+
+tags:
+- llama3.2
+- abliterated
+- uncensored
+---
+# MicroThinker-3B-Preview
+
+MicroThinker-3B-Preview, a new model fine-tuned from the [huihui-ai/Llama-3.2-3B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated) model, focused on advancing AI reasoning capabilities. 
+
+## Training Details
+
+This is just a test, but the performance is quite good. 
+
+The model is still being fine-tuned, but it will be ready very soon.
+
+Now, I'll introduce the test environment.
+
+The model was trained using 1 RTX 4090 GPU(24GB) .
+
+The fine-tuning process used only 20,000 records from each dataset.
+
+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.
+
+```
+conda create -yn ms-swift python=3.11
+conda activate ms-swift
+
+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-3.2-3B-Instruct-abliterated --local-dir ./huihui-ai/Llama-3.2-3B-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-3.2-3B-Instruct-abliterated --model_type llama3_2 --train_type lora --dataset "data/QWQ-LONGCOT-500K/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-3.2-3B-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-3.2-3B-Instruct-abliterated --adapters output/Llama-3.2-3B-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
+```
+
+
+6. 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-LONGCOT-500K/qwq_500k.jsonl#20000" "data/LONGCOT-Refine-500K/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-3.2-3B-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"
+```
+
+
+7. Save the final fine-tuned model.
+Replace the directories below with specific ones.
+
+```
+swift infer --model huihui-ai/checkpoint-1237-merged --adapters output/Llama-3.2-3B-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-3B-Preview`, Copy or move this directory to the `huihui` directory.
+
+8. Perform inference on the final fine-tuned model.
+
+```
+swift infer --model huihui/MicroThinker-3B-Preview --stream true --infer_backend pt --max_new_tokens 8192
+```
+
+9. Test examples.
+
+```
+How many 'r' characters are there in the word "strawberry"?
+```