Update README.md

README.md

@@ -1,3 +1,82 @@
 ---
 license: apache-2.0
+datasets:
+- squarelike/sharegpt_deepl_ko_translation
+language:
+- en
+- ko
+pipeline_tag: translation
 ---
+
+# Gugugo-koen-7B-V1.1-GPTQ
+Detail repo: [https://github.com/jwj7140/Gugugo](https://github.com/jwj7140/Gugugo)
+![Gugugo](./logo.png)
+
+This is GGUF model from [squarelike/Gugugo-koen-7B-V1.1](https://huggingface.co/squarelike/Gugugo-koen-7B-V1.1)
+
+**Base Model**: [Llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b)
+
+**Training Dataset**: [sharegpt_deepl_ko_translation](https://huggingface.co/datasets/squarelike/sharegpt_deepl_ko_translation).
+
+I trained with 1x A6000 GPUs for 90 hours.
+
+## **Prompt Template**
+**KO->EN**
+```
+### 한국어: {sentence}</끝>
+### 영어:
+```
+**EN->KO**
+```
+### 영어: {sentence}</끝>
+### 한국어:
+```
+
+## **Implementation Code**
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList
+import torch
+repo = "squarelike/Gugugo-koen-7B-V1.1"
+model = AutoModelForCausalLM.from_pretrained(
+        repo,
+        load_in_4bit=True
+        device_map='auto'
+)
+tokenizer = AutoTokenizer.from_pretrained(repo)
+
+class StoppingCriteriaSub(StoppingCriteria):
+    def __init__(self, stops = [], encounters=1):
+        super().__init__()
+        self.stops = [stop for stop in stops]
+
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor):
+        for stop in self.stops:
+            if torch.all((stop == input_ids[0][-len(stop):])).item():
+                return True
+
+        return False
+
+stop_words_ids = torch.tensor([[829, 45107, 29958], [1533, 45107, 29958], [829, 45107, 29958], [21106, 45107, 29958]]).to("cuda")
+stopping_criteria = StoppingCriteriaList([StoppingCriteriaSub(stops=stop_words_ids)])
+
+def gen(lan="en", x=""):
+    if (lan == "ko"):
+        prompt = f"### 한국어: {x}</끝>\n### 영어:"
+    else:
+        prompt = f"### 영어: {x}</끝>\n### 한국어:"
+    gened = model.generate(
+        **tokenizer(
+            prompt,
+            return_tensors='pt',
+            return_token_type_ids=False
+        ).to("cuda"),
+        max_new_tokens=2000,
+        temperature=0.1,
+        do_sample=True,
+        stopping_criteria=stopping_criteria
+    )
+    return tokenizer.decode(gened[0][1:]).replace(prompt+" ", "").replace("</끝>", "")
+
+
+print(gen(lan="en", x="Hello, world!"))
+```