aaabiao Anitaliu98 commited on
Commit
c93cc24
1 Parent(s): 1f1bfe1

Create README.md (#2)

Browse files

- Create README.md (3568c07e520905915bf4d7793e5ede18a362b193)


Co-authored-by: XUELING LIU <Anitaliu98@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +59 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - code
7
+ ---
8
+
9
+ <h1 align="center"> OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement<h1>
10
+
11
+ <p align="center">
12
+ <img width="1000px" alt="OpenCodeInterpreter" src="https://opencodeinterpreter.github.io/static/images/figure1.png">
13
+ </p>
14
+ <p align="center">
15
+ <a href="https://opencodeinterpreter.github.io/">[🏠Homepage]</a>
16
+ |
17
+ <a href="https://github.com/OpenCodeInterpreter/OpenCodeInterpreter/">[🛠️Code]</a>
18
+ </p>
19
+ <hr>
20
+
21
+ ## Introduction
22
+ OpenCodeInterpreter is a family of open-source code generation systems designed to bridge the gap between large language models and advanced proprietary systems like the GPT-4 Code Interpreter. It significantly advances code generation capabilities by integrating execution and iterative refinement functionalities.
23
+
24
+ ## Model Usage
25
+ ### Inference
26
+
27
+ ```python
28
+ import torch
29
+ from transformers import AutoTokenizer, AutoModelForCausalLM
30
+ model_path="OpenCodeInterpreter-DS-33B"
31
+
32
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
33
+ model = AutoModelForCausalLM.from_pretrained(
34
+ model_path,
35
+ torch_dtype=torch.bfloat16,
36
+ device_map="auto",
37
+ )
38
+ model.eval()
39
+
40
+ prompt = "Write a function to find the shared elements from the given two lists."
41
+ inputs = tokenizer.apply_chat_template(
42
+ [{'role': 'user', 'content': prompt }],
43
+ return_tensors="pt"
44
+ ).to(model.device)
45
+ outputs = model.generate(
46
+ inputs,
47
+ max_new_tokens=1024,
48
+ do_sample=False,
49
+ pad_token_id=tokenizer.eos_token_id,
50
+ eos_token_id=tokenizer.eos_token_id,
51
+ )
52
+ print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
53
+ ```
54
+
55
+
56
+ ## Contact
57
+
58
+ If you have any inquiries, please feel free to raise an issue or reach out to us via email at: xiangyue.work@gmail.com, zhengtianyu0428@gmail.com.
59
+ We're here to assist you!"