Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
|
@@ -15,7 +15,6 @@ MODEL_NAME = MODELS.split("/")[-1]
|
|
| 15 |
TITLE = "<h1><center>raspberry-3b</center></h1>"
|
| 16 |
|
| 17 |
DESCRIPTION = f"""
|
| 18 |
-
<h3>MODEL: <a href="https://hf.co/{MODELS}">{MODEL_NAME}</a></h3>
|
| 19 |
<center>
|
| 20 |
<p>raspberry-3b
|
| 21 |
<br>
|
|
@@ -37,11 +36,11 @@ h3 {
|
|
| 37 |
"""
|
| 38 |
|
| 39 |
model = AutoModelForCausalLM.from_pretrained(
|
| 40 |
-
|
| 41 |
torch_dtype=torch.float16,
|
| 42 |
device_map="auto",
|
| 43 |
)
|
| 44 |
-
tokenizer = AutoTokenizer.from_pretrained(
|
| 45 |
|
| 46 |
@spaces.GPU
|
| 47 |
def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
|
|
|
|
| 15 |
TITLE = "<h1><center>raspberry-3b</center></h1>"
|
| 16 |
|
| 17 |
DESCRIPTION = f"""
|
|
|
|
| 18 |
<center>
|
| 19 |
<p>raspberry-3b
|
| 20 |
<br>
|
|
|
|
| 36 |
"""
|
| 37 |
|
| 38 |
model = AutoModelForCausalLM.from_pretrained(
|
| 39 |
+
MODEL_ID,
|
| 40 |
torch_dtype=torch.float16,
|
| 41 |
device_map="auto",
|
| 42 |
)
|
| 43 |
+
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
| 44 |
|
| 45 |
@spaces.GPU
|
| 46 |
def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int, top_p: float, top_k: int, penalty: float):
|