Update README.md

README.md

@@ -11,3 +11,74 @@ tags:
 - orpo
 ---
 
+
+
+# Model Summary
+
+Gemma-2-9B-Chinese-Chat is the first instruction-tuned language model built upon [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) for Chinese & English users with various abilities such as roleplaying & tool-using.
+
+Developed by: [Shenzhi Wang](https://shenzhi-wang.netlify.app) (王慎执) and [Yaowei Zheng](https://github.com/hiyouga) (郑耀威)
+
+- License: [Gemma License](https://ai.google.dev/gemma/terms)
+- Base Model: [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it)
+- Model Size: 9.24B
+- Context length: 8K
+
+# 1. Introduction
+
+This is the first model specifically fine-tuned for Chinese & English users based on the [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) with a preference dataset with more than 100K preference pairs. The fine-tuning algorithm we employ is ORPO [1].
+
+**Compared to the original [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it), our Gemma-2-9B-Chinese-Chat model significantly reduces the issues of "Chinese questions with English answers" and the mixing of Chinese and English in responses, with enhanced performance in roleplay, tool using, and math.**
+
+[1] Hong, Jiwoo, Noah Lee, and James Thorne. "Reference-free Monolithic Preference Optimization with Odds Ratio." arXiv preprint arXiv:2403.07691 (2024).
+
+Training framework: [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory).
+
+Training details:
+
+- epochs: 3
+- learning rate: 3e-6
+- learning rate scheduler type: cosine
+- Warmup ratio: 0.1
+- cutoff len (i.e. context length): 8192
+- orpo beta (i.e. $\lambda$ in the ORPO paper): 0.05
+- global batch size: 128
+- fine-tuning type: full parameters
+- optimizer: paged_adamw_32bit
+
+# 2. Usage
+
+Please upgrade the `transformers` package to ensure it supports Gemma-2 models. The current version we are using is `4.42.2`.
+
+```python
+import torch
+import transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "shenzhi-wang/Gemma-2-9B-Chinese-Chat"
+dtype = torch.bfloat16
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="cuda",
+    torch_dtype=dtype,
+)
+
+chat = [
+    {"role": "user", "content": "写一首关于机器学习的诗。"},
+]
+input_ids = tokenizer.apply_chat_template(
+    chat, tokenize=True, add_generation_prompt=True, return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=8192,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1] :]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```