Update README.md

README.md

@@ -1,3 +1,41 @@
 ---
 license: other
+language:
+- en
+pipeline_tag: text2text-generation
+tags:
+- alpaca
+- llama
+- chat
+- gpt4
 ---
+# GPT4 Alpaca LoRA 30B HF
+
+This is a pre-merged version of the [Chansung GPT4 Alpaca 30B LoRA model](https://huggingface.co/chansung/gpt4-alpaca-lora-30b).
+
+It was created by merging the LoRA provided in the above repo with the original Llama 30B model.
+
+You will need at least 60GB VRAM to use this model.
+
+For a [GPTQ](https://github.com/qwopqwop200/GPTQ-for-LLaMa) quantized 4bit model, usable on a 24GB GPU, see: [GPT4-Alpaca-LoRA-30B-HF](https://huggingface.co/TheBloke/gpt4-alpaca-lora-30B-GPTQ-4bit-128g)
+
+# Original GPT4 Alpaca Lora model card
+
+This repository comes with LoRA checkpoint to make LLaMA into a chatbot like language model. The checkpoint is the output of instruction following fine-tuning process with the following settings on 8xA100(40G) DGX system.
+- Training script: borrowed from the official [Alpaca-LoRA](https://github.com/tloen/alpaca-lora) implementation
+- Training script:
+```shell
+python finetune.py \
+    --base_model='decapoda-research/llama-30b-hf' \
+    --data_path='alpaca_data_gpt4.json' \
+    --num_epochs=10 \
+    --cutoff_len=512 \
+    --group_by_length \
+    --output_dir='./gpt4-alpaca-lora-30b' \
+    --lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
+    --lora_r=16 \
+    --batch_size=... \
+    --micro_batch_size=...
+```
+
+You can find how the training went from W&B report [here](https://wandb.ai/chansung18/gpt4_alpaca_lora/runs/w3syd157?workspace=user-chansung18).