Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
|
@@ -7,8 +7,6 @@ import os
|
|
| 7 |
import time
|
| 8 |
|
| 9 |
|
| 10 |
-
|
| 11 |
-
|
| 12 |
HF_TOKEN = os.environ.get("HF_TOKEN", None)
|
| 13 |
MODEL_ID = "CohereForAI/aya-23-8B"
|
| 14 |
MODEL_NAME = MODEL_ID.split("/")[-1]
|
|
@@ -74,7 +72,11 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
|
|
| 74 |
temperature=temperature,
|
| 75 |
)
|
| 76 |
|
| 77 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
|
| 79 |
return gen_text
|
| 80 |
|
|
|
|
| 7 |
import time
|
| 8 |
|
| 9 |
|
|
|
|
|
|
|
| 10 |
HF_TOKEN = os.environ.get("HF_TOKEN", None)
|
| 11 |
MODEL_ID = "CohereForAI/aya-23-8B"
|
| 12 |
MODEL_NAME = MODEL_ID.split("/")[-1]
|
|
|
|
| 72 |
temperature=temperature,
|
| 73 |
)
|
| 74 |
|
| 75 |
+
gen_tokens = [
|
| 76 |
+
gt[prompt_padded_len:] for gt in gen_tokens
|
| 77 |
+
]
|
| 78 |
+
|
| 79 |
+
gen_text = tokenizer.batch_decode(gen_tokens, skip_special_tokens=True)
|
| 80 |
|
| 81 |
return gen_text
|
| 82 |
|