Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
|
@@ -5,7 +5,7 @@ import spaces
|
|
| 5 |
import torch
|
| 6 |
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
|
| 7 |
|
| 8 |
-
MAX_NEW_TOKENS =
|
| 9 |
MODEL_NAME = "Azure99/Blossom-V6.1-8B"
|
| 10 |
|
| 11 |
model = AutoModelForCausalLM.from_pretrained(
|
|
@@ -29,7 +29,6 @@ def get_input_ids(inst, history):
|
|
| 29 |
)
|
| 30 |
|
| 31 |
|
| 32 |
-
@spaces.GPU(duration=60)
|
| 33 |
def chat(inst, history, temperature, top_p, repetition_penalty):
|
| 34 |
streamer = TextIteratorStreamer(
|
| 35 |
tokenizer, skip_prompt=True, skip_special_tokens=True
|
|
|
|
| 5 |
import torch
|
| 6 |
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
|
| 7 |
|
| 8 |
+
MAX_NEW_TOKENS = 4096
|
| 9 |
MODEL_NAME = "Azure99/Blossom-V6.1-8B"
|
| 10 |
|
| 11 |
model = AutoModelForCausalLM.from_pretrained(
|
|
|
|
| 29 |
)
|
| 30 |
|
| 31 |
|
|
|
|
| 32 |
def chat(inst, history, temperature, top_p, repetition_penalty):
|
| 33 |
streamer = TextIteratorStreamer(
|
| 34 |
tokenizer, skip_prompt=True, skip_special_tokens=True
|