codefuse-ai
/

CodeFuse-13B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

codefuse-admin commited on Sep 12, 2023

Commit

0074412

•

1 Parent(s): 8d41a21

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -30,8 +30,8 @@ CodeFuse-13B is a 13 billion parameter code generation model trained on the GPT-
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained(("CodeFuse-13B-evol-instruct-4k"))
-model = AutoModelForCausalLM.from_pretrained(("CodeFuse-13B-evol-instruct-4k"), device_map="auto").half().eval()
 input_ids = tokenizer.encode("# language: Python\ndef quick_sort(array):\n", return_tensors="pt").to("cuda")
 output_ids = model.generate(input_ids, max_new_tokens=200)
@@ -70,8 +70,8 @@ CodeFuse-13B是基于GPT-NeoX框架训练的13B参数代码生成模型，能够
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained(("CodeFuse-13B-evol-instruct-4k"))
-model = AutoModelForCausalLM.from_pretrained(("CodeFuse-13B-evol-instruct-4k"), device_map="auto").half().eval()
 input_ids = tokenizer.encode("# language: Python\ndef quick_sort(array):\n", return_tensors="pt").to("cuda")
 output_ids = model.generate(input_ids, max_new_tokens=200)

 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(("CodeFuse-13B"))
+model = AutoModelForCausalLM.from_pretrained(("CodeFuse-13B"), device_map="auto").half().eval()
 input_ids = tokenizer.encode("# language: Python\ndef quick_sort(array):\n", return_tensors="pt").to("cuda")
 output_ids = model.generate(input_ids, max_new_tokens=200)
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(("CodeFuse-13B"))
+model = AutoModelForCausalLM.from_pretrained(("CodeFuse-13B"), device_map="auto").half().eval()
 input_ids = tokenizer.encode("# language: Python\ndef quick_sort(array):\n", return_tensors="pt").to("cuda")
 output_ids = model.generate(input_ids, max_new_tokens=200)