Update README.md

README.md

@@ -1,3 +1,35 @@
 ---
 license: apache-2.0
 ---
+RWKV-4-World-1.5B的Hugface格式，因新版World的tokenizer较之前Raven\Pile版本有较大变化，因而需要进行新版HF适配
+ringrwkv兼容了原生rwkv库和transformers的rwkv库，同时新添入World版本的配置及代码（默认1.5B），并修复了原HF的RWKV在
+Forward RWKVOutput时的细微问题，主要是引入和明确last_hidden_state。以下是轻量级使用代码，比较方便：<br>
+
+import torch<br>
+from ringrwkv.configuration_rwkv_world import RwkvConfig<br>
+from ringrwkv.rwkv_tokenizer import TRIE_TOKENIZER<br>
+from ringrwkv.modehf_world import RwkvForCausalLM<br>
+
+
+model = RwkvForCausalLM.from_pretrained("StarRing2022/RWKV-4-World-1.5B")<br> #或将本模型下载至本地文件夹
+tokenizer = TRIE_TOKENIZER('./ringrwkv/rwkv_vocab_v20230424.txt')<br>
+     
+text = "你叫什么名字？"<br>
+
+question = f'Question: {text.strip()}\n\nAnswer:'<br>
+
+input_ids = tokenizer.encode(question)<br>
+input_ids = torch.tensor(input_ids).unsqueeze(0)<br>
+
+out = model.generate(input_ids,max_new_tokens=40)<br><br>
+
+
+outlist = out[0].tolist()<br>
+
+for i  in outlist:<br>
+  &nbsp;&nbsp;&nbsp;&nbsp;if i==0:<br> #要删除tokenid为0的元素
+  &nbsp;&nbsp;&nbsp;&nbsp;outlist.remove(i)<br>
+
+answer = tokenizer.decode(outlist)<br>
+
+print(answer)<br>