Update README.md

README.md

@@ -33,13 +33,66 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **Paper [optional]:** [More Information Needed]
 - **Demo [optional]:** [More Information Needed]
 
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+## Driectly Uses
+
+```
+
+from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline
+from peft import PeftModelForCausalLM
+from transformers import BitsAndBytesConfig
+base_model = "ljcnju/DeepSeek7bForCodeTrans"
+tokenzier = AutoTokenizer.from_pretrained(base_model)
+babcfig = BitsAndBytesConfig(load_in_8bit=True,llm_int8_enable_fp32_cpu_offload=True)
+basemodel = "deepseek-ai/deepseek-coder-6.7b-base"
+model = AutoModelForCausalLM.from_pretrained(basemodel,
+        device_map = "cuda:0",
+        quantization_config = babcfig)
+model.resize_token_embeddings(len(tokenzier))
+
+model = PeftModelForCausalLM.from_pretrained(model,base_model)
+
+prompt = "<|translate|> public void removePresentationFormat() {remove1stProperty(PropertyIDMap.PID_PRESFORMAT);}\n<|end_of_c-sharp_code|><|begin_of_c-sharp_code|>"
+input = tokenzier(prompt,return_tensors="pt")
+output_ids = model.generate(**input)
+print(tokenzier.batch_decode(output_ids))
+
+```
+
+### Use with vLLM
+
+```
+
+from vllm import LLM, SamplingParams,EngineArgs, LLMEngine, RequestOutput
+from vllm.lora.request import LoRARequest
+engine_args = EngineArgs(model="deepseek-ai/deepseek-coder-6.7b-base",
+                             enable_lora=True,
+                             max_loras=1,
+                             max_lora_rank=8,
+                             max_cpu_loras=2,
+                             max_num_seqs=256,
+                             max_model_len= 512)
+engine = LLMEngine.from_engine_args(engine_args)
+lorarequest = LoRARequest("DeepSeek7bForCodeTrans",1,"ljcnju/DeepSeek7bForCodeTrans")
+engine.add_lora(lorarequest)
+
+additional_special_tokens = {'additional_special_tokens':['<|begin_of_java_code|>','<|end_of_java_code|>'\
+                                                           ,'<|begin_of_c-sharp_code|>','<|end_of_c-sharp_code|>',\
+                                                            '<|translate|>']}
+prompt = "public void serialize(LittleEndianOutput out) {out.writeShort(field_1_vcenter);}\n"
+prompt = additional_special_tokens['additional_special_tokens'][0] + prompt + additional_special_tokens['additional_special_tokens'][1] + additional_special_tokens['additional_special_tokens'][2]
+
+sampling_params = SamplingParams(temperature=0.1,max_tokens= 512,stop_token_ids=[32022,32014],skip_special_tokens=False)
+engine.add_request(str(1),prompt,sampling_params,lora_request=lorarequest)
+engine.step()
+real_output = ""
+finished = False
+while engine.has_unfinished_requests():
+    request_outputs  =  engine.step()
+    for request_output in request_outputs:
+        finished = finished | request_output.finished
+print(request_outputs[0].outputs[0].text)
+
+```
 
 [More Information Needed]