Update README.md

README.md

@@ -8,7 +8,7 @@ language:
 pipeline_tag: translation
 ---
 
-# Gugugo-koen-7B-V1.1-GPTQ
+# Gugugo-koen-7B-V1.1-GGUF
 Detail repo: [https://github.com/jwj7140/Gugugo](https://github.com/jwj7140/Gugugo)
 ![Gugugo](./logo.png)
 
@@ -30,53 +30,4 @@ I trained with 1x A6000 GPUs for 90 hours.
 ```
 ### 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!"))
 ```