Update README_zh.md

README_zh.md

@@ -63,109 +63,6 @@ with torch.no_grad():
     print(out)
 ```
 
-利用[NBCE](https://github.com/bojone/NBCE/tree/main)进行推理
-
-```python
-import json
-import torch
-from transformers import AutoTokenizer
-from transformers import AutoModelForCausalLM
-from transformers import TopPLogitsWarper, LogitsProcessorList
-import pdb
-
-# 加载tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-tokenizer.padding_side = 'left' 
-tokenizer.pad_token = tokenizer.unk_token
-
-# 加载Aquila模型
-model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.float16)
-device = torch.device('cuda')
-model.to(device)
-# 加载示例Context
-from cyg_conversation import default_conversation
-
-conv = default_conversation.copy()
-contexts = json.load(open('code_text_2.json'))
-
-question = "请解释这段程序的功能："
-batch = []
-conv.append_message(conv.roles[0], question)
-conv.append_message(conv.roles[1], None)
-batch.append(conv.get_prompt())
-# 拼接context和question
-for ci,context in enumerate(contexts):        
-    conv1 = default_conversation.copy()
-    conv1.append_message(conv.roles[0], context+question)
-    conv1.append_message(conv.roles[1], None)
-    batch.append(conv1.get_prompt())
-print('Context长度分布：', [len(text) for text in batch])
-print('Context总长度：', sum([len(text) for text in batch]))
-
-# Top-P截断
-processors = LogitsProcessorList()
-processors.append(TopPLogitsWarper(0.95))
-
-# Copied from https://github.com/bojone/NBCE/blob/main/test.py#L51-L106
-@torch.inference_mode()
-def generate(max_tokens):
-    """Naive Bayes-based Context Extension 演示代码
-    """
-    inputs = tokenizer(batch, padding='longest', return_tensors='pt').to(device)
-    input_ids = inputs.input_ids
-    attention_mask = inputs.attention_mask
-    
-    print('input_ids', input_ids.shape)
-    past_key_values = None
-    n = input_ids.shape[0]
-    
-    for i in range(max_tokens):
-        # 模型输出
-        outputs = model(input_ids=input_ids,
-                        attention_mask=attention_mask,
-                        return_dict=True,
-                        use_cache=True,
-                        past_key_values=past_key_values
-                       )
-        past_key_values = outputs.past_key_values
-        
-        # ===== 核心代码开始 =====
-        beta, eta = 0.25, 0.1
-        logits = outputs.logits[:, -1]
-        logits = logits - logits.logsumexp(dim=-1, keepdims=True)
-        logits = processors(input_ids, logits)
-        entropy = -(logits.exp() * logits.clip(-100, 0)).sum(dim=-1)
-        if i > 0:
-            entropy[k] -= eta
-        k = entropy[1:].argmin() + 1
-        logits_max = logits[k]
-        logits_uncond = logits[0]
-        logits_merged = (1 + beta) * logits_max - beta * logits_uncond
-        logits = torch.where(logits_uncond > -100, logits_merged, logits_max)
-        # ===== 核心代码结束 =====
-        
-        # 构建分布，采样
-        # tau = 1是标准的随机采样，tau->0则是贪心搜索
-        # 简单起见，这里没有实现topk、topp截断
-        tau = 0.01
-        probas = torch.nn.functional.softmax(logits[None] / tau , dim=-1)
-        next_tokens = torch.multinomial(probas, num_samples=1).squeeze(1)        
-        if next_tokens[0] == tokenizer.eos_token_id:
-            break
-            
-        ret = tokenizer.batch_decode(next_tokens)
-        print(ret[0], flush=True, end='')
-        
-        # prepare for next iteration
-        input_ids = next_tokens.unsqueeze(-1).tile(n, 1)
-        attention_mask = torch.cat([attention_mask, torch.ones(n, 1, dtype=torch.long, device=device)], dim=-1)        
-
-
-if __name__ == '__main__':
-    generate(1000)
-
-```
-
 
 ## 证书/License