deepseekmirror/DeepSeek-Coder
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-Coder.git synced 2025-06-20 00:14:03 -04:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
ZHU QIHAO 2023-10-31 11:11:09 +08:00 committed by GitHub
parent 1ab77f7208
commit c6ebdafb13
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -51,8 +51,8 @@ Here give some examples of how to use our model.
```python ```python
from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import AutoTokenizer, AutoModelForCausalLM
import torch import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True).cuda() model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True).cuda()
input_text = "#write a quick sort algorithm" input_text = "#write a quick sort algorithm"
inputs = tokenizer(input_text, return_tensors="pt").cuda() inputs = tokenizer(input_text, return_tensors="pt").cuda()
outputs = model.generate(**inputs, max_length=128) outputs = model.generate(**inputs, max_length=128)
@ -78,8 +78,8 @@ def quick_sort(arr):
```python ```python
from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import AutoTokenizer, AutoModelForCausalLM
import torch import torch
tokenizer = AutoTokenizer.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True).cuda() model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True).cuda()
input_text = """<fim_prefix>def quick_sort(arr): input_text = """<fim_prefix>def quick_sort(arr):
if len(arr) <= 1: if len(arr) <= 1:
return arr return arr
@ -103,8 +103,8 @@ This code will output the following result:
#### 3）Repository Level Code Completion #### 3）Repository Level Code Completion
```python ```python
from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True).cuda() model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True).cuda()
input_text = """#utils.py input_text = """#utils.py
import torch import torch
@ -193,8 +193,8 @@ In the following scenario, the Deepseek-Coder 7B model effectively calls a class
#### 4）Chat Model Inference #### 4）Chat Model Inference
```python ```python
from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek/deepseek-coder-7b-base", trust_remote_code=True).cuda() model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-7b-base", trust_remote_code=True).cuda()
prompt = "write a quick sort algorithm in python." prompt = "write a quick sort algorithm in python."
prompt = f"""Below is an instruction that describes a task, paired with an input that provides further context.\nWrite a response that appropriately completes the request.\n\n### Instruction:\nWrite a program to perform the given task.\n\nInput:\n{prompt}\n\n### Response:\n""" prompt = f"""Below is an instruction that describes a task, paired with an input that provides further context.\nWrite a response that appropriately completes the request.\n\n### Instruction:\nWrite a program to perform the given task.\n\nInput:\n{prompt}\n\n### Response:\n"""
inputs = tokenizer.encode(prompt, return_tensors="pt").cuda() inputs = tokenizer.encode(prompt, return_tensors="pt").cuda()