Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -13,7 +13,6 @@ def tokenize(input_text):
|
|
13 |
phi3_tokens = len(phi3_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
14 |
t5_tokens = len(t5_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
15 |
gemma_tokens = len(gemma_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
16 |
-
gemma2_tokens = len(gemma2_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
17 |
command_r_tokens = len(command_r_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
18 |
qwen_tokens = len(qwen_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
19 |
codeqwen_tokens = len(codeqwen_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
@@ -33,8 +32,7 @@ def tokenize(input_text):
|
|
33 |
"Phi-1/Phi-2": phi2_tokens,
|
34 |
"Phi-3": phi3_tokens,
|
35 |
"T5": t5_tokens,
|
36 |
-
"Gemma": gemma_tokens,
|
37 |
-
"Gemma-2": gemma2_tokens,
|
38 |
"Command-R": command_r_tokens,
|
39 |
"Qwen/Qwen1.5": qwen_tokens,
|
40 |
"CodeQwen": codeqwen_tokens,
|
@@ -62,7 +60,6 @@ if __name__ == "__main__":
|
|
62 |
phi3_tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
63 |
t5_tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xxl")
|
64 |
gemma_tokenizer = AutoTokenizer.from_pretrained("alpindale/gemma-2b")
|
65 |
-
gemma2_tokenizer = AutoTokenizer.from_pretrained("UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3")
|
66 |
command_r_tokenizer = AutoTokenizer.from_pretrained("PJMixers/CohereForAI_c4ai-command-r-plus-tokenizer")
|
67 |
qwen_tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-7B")
|
68 |
codeqwen_tokenizer = AutoTokenizer.from_pretrained("Qwen/CodeQwen1.5-7B")
|
@@ -72,5 +69,5 @@ if __name__ == "__main__":
|
|
72 |
internlm_tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-20b", trust_remote_code=True)
|
73 |
internlm2_tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-20b", trust_remote_code=True)
|
74 |
|
75 |
-
iface = gr.Interface(fn=tokenize, inputs=gr.Textbox(label="Input Text", lines=
|
76 |
iface.launch()
|
|
|
13 |
phi3_tokens = len(phi3_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
14 |
t5_tokens = len(t5_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
15 |
gemma_tokens = len(gemma_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
|
|
16 |
command_r_tokens = len(command_r_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
17 |
qwen_tokens = len(qwen_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
18 |
codeqwen_tokens = len(codeqwen_tokenizer(input_text, add_special_tokens=True)["input_ids"])
|
|
|
32 |
"Phi-1/Phi-2": phi2_tokens,
|
33 |
"Phi-3": phi3_tokens,
|
34 |
"T5": t5_tokens,
|
35 |
+
"Gemma/Gemma-2": gemma_tokens,
|
|
|
36 |
"Command-R": command_r_tokens,
|
37 |
"Qwen/Qwen1.5": qwen_tokens,
|
38 |
"CodeQwen": codeqwen_tokens,
|
|
|
60 |
phi3_tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
61 |
t5_tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xxl")
|
62 |
gemma_tokenizer = AutoTokenizer.from_pretrained("alpindale/gemma-2b")
|
|
|
63 |
command_r_tokenizer = AutoTokenizer.from_pretrained("PJMixers/CohereForAI_c4ai-command-r-plus-tokenizer")
|
64 |
qwen_tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-7B")
|
65 |
codeqwen_tokenizer = AutoTokenizer.from_pretrained("Qwen/CodeQwen1.5-7B")
|
|
|
69 |
internlm_tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-20b", trust_remote_code=True)
|
70 |
internlm2_tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-20b", trust_remote_code=True)
|
71 |
|
72 |
+
iface = gr.Interface(fn=tokenize, inputs=gr.Textbox(label="Input Text", lines=19), outputs="text")
|
73 |
iface.launch()
|