Training in progress, epoch 1

README.md

@@ -33,62 +33,13 @@ 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]
 
-## Driectly Uses
-
-```Python
-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
-
-```Python
-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)
-```
+## 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. -->
 
 [More Information Needed]
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
+  "base_model_name_or_path": "../../../../Models/deepseek-ai/deepseek-coder-6.7b-base",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5755eacccb10dfbc388cd956b5ae73c56948dcd7373f121d10b114862fa8d61
+oid sha256:6619ac0331fff08fef952de1121907f36a29d7979022859cbb6d18be8023c846
 size 16794200

special_tokens_map.json

@@ -1,14 +1,14 @@
 {
   "additional_special_tokens": [
     {
-      "content": "<|end_of_c-sharp_code|>",
+      "content": "<|begin_of_java_code|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<|translate|>",
+      "content": "<|end_of_java_code|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -22,14 +22,14 @@
       "single_word": false
     },
     {
-      "content": "<|end_of_java_code|>",
+      "content": "<|end_of_c-sharp_code|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<|begin_of_java_code|>",
+      "content": "<|translate|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 32014,
+    "pad_type_id": 0,
+    "pad_token": "<｜end▁of▁sentence｜>"
+  },
   "added_tokens": [
     {
       "id": 32000,
@@ -203,7 +217,7 @@
     },
     {
       "id": 32022,
-      "content": "<|end_of_c-sharp_code|>",
+      "content": "<|begin_of_java_code|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -212,7 +226,7 @@
     },
     {
       "id": 32023,
-      "content": "<|translate|>",
+      "content": "<|end_of_java_code|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -230,7 +244,7 @@
     },
     {
       "id": 32025,
-      "content": "<|end_of_java_code|>",
+      "content": "<|end_of_c-sharp_code|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -239,7 +253,7 @@
     },
     {
       "id": 32026,
-      "content": "<|begin_of_java_code|>",
+      "content": "<|translate|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "32000": {
       "content": "õ",
@@ -177,7 +179,7 @@
       "special": false
     },
     "32022": {
-      "content": "<|end_of_c-sharp_code|>",
+      "content": "<|begin_of_java_code|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -185,7 +187,7 @@
       "special": true
     },
     "32023": {
-      "content": "<|translate|>",
+      "content": "<|end_of_java_code|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -201,7 +203,7 @@
       "special": true
     },
     "32025": {
-      "content": "<|end_of_java_code|>",
+      "content": "<|end_of_c-sharp_code|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -209,7 +211,7 @@
       "special": true
     },
     "32026": {
-      "content": "<|begin_of_java_code|>",
+      "content": "<|translate|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -218,11 +220,11 @@
     }
   },
   "additional_special_tokens": [
-    "<|end_of_c-sharp_code|>",
-    "<|translate|>",
-    "<|begin_of_c-sharp_code|>",
+    "<|begin_of_java_code|>",
     "<|end_of_java_code|>",
-    "<|begin_of_java_code|>"
+    "<|begin_of_c-sharp_code|>",
+    "<|end_of_c-sharp_code|>",
+    "<|translate|>"
   ],
   "bos_token": "<｜begin▁of▁sentence｜>",
   "clean_up_tokenization_spaces": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db357bcd7b7f80f2bae124a5c6ab6172f381e1b216336d366d7280c6af68d384
-size 4600
+oid sha256:000f9e1abb31dbbe1028a90de5727cce3c3fc08165a092df1078608a63d4581e
+size 4728