Update README.md

README.md

@@ -32,9 +32,9 @@ CodeFuse-DeepSeek-33B is a 33B Code-LLM finetuned by QLoRA on multiple code-rela
 
 🔥🔥 2023-09-27 CodeFuse-StarCoder-15B has been released, achieving a pass@1 (greedy decoding) score of 54.9% on HumanEval, which is a 21% increase compared to StarCoder's 33.6%.
 
-🔥🔥 2023-09-26 We are pleased to announce the release of the [4-bit quantized version](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B-4bits/summary) of [CodeFuse-CodeLlama-34B](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B/summary). Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
+🔥🔥 2023-09-26 We are pleased to announce the release of the 4-bit quantized version of CodeFuse-CodeLlama-34B. Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
 
-🔥🔥 2023-09-11 [CodeFuse-CodeLlama34B](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B/summary) has achieved 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
+🔥🔥 2023-09-11 CodeFuse-CodeLlama-34B has achieved 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
 
 <br>
 
@@ -44,7 +44,6 @@ CodeFuse-DeepSeek-33B is a 33B Code-LLM finetuned by QLoRA on multiple code-rela
 
 + If you wish to fine-tune the model yourself, you can visit ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
 
-+ If you wish to deploy the model yourself, you can visit ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
 
 + If you wish to see a demo of the model, you can visit ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨
 
@@ -156,16 +155,18 @@ Specifically, we also add the Programming Language Tag (e.g. "```# language: Pyt
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
- 
+
+model_dir = "codefuse-ai/CodeFuse-DeepSeek-33B"
+
 def load_model_tokenizer(model_path):
-    tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/CodeFuse-DeepSeek-33B", trust_remote_code=True)
+    tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
     tokenizer.eos_token = "<｜end▁of▁sentence｜>"
     tokenizer.pad_token = "<｜end▁of▁sentence｜>"
     tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids(tokenizer.eos_token)
     tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids(tokenizer.pad_token)
     tokenizer.padding_side = "left"
     
-    model = AutoModelForCausalLM.from_pretrained('codefuse-ai/CodeFuse-DeepSeek-33B', device_map='auto',torch_dtype=torch.bfloat16, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(model_path, device_map='auto',torch_dtype=torch.bfloat16, trust_remote_code=True)
     return model, tokenizer
 
 
@@ -341,19 +342,20 @@ def separate_paren_groups(paren_string: str) -> List[str]:
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
- 
+
+model_dir = "codefuse-ai/CodeFuse-DeepSeek-33B"
+
 def load_model_tokenizer(model_path):
-    tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/CodeFuse-DeepSeek-33B", trust_remote_code=True, use_fast=False, legacy=False)
+    tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
     tokenizer.eos_token = "<｜end▁of▁sentence｜>"
     tokenizer.pad_token = "<｜end▁of▁sentence｜>"
     tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids(tokenizer.eos_token)
     tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids(tokenizer.pad_token)
     tokenizer.padding_side = "left"
     
-    model = AutoModelForCausalLM.from_pretrained('codefuse-ai/CodeFuse-DeepSeek-33B', device_map='auto',torch_dtype=torch.bfloat16, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(model_path, device_map='auto',torch_dtype=torch.bfloat16, trust_remote_code=True)
     return model, tokenizer
 
-
 HUMAN_ROLE_START_TAG = "<s>human\n"
 BOT_ROLE_START_TAG = "<s>bot\n"