Update app.py
Browse files
app.py
CHANGED
@@ -7,7 +7,7 @@ from huggingface_hub import hf_hub_download
|
|
7 |
subprocess.run('pip install llama-cpp-python==0.2.75 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124', shell=True)
|
8 |
subprocess.run('pip install llama-cpp-agent==0.2.10', shell=True)
|
9 |
|
10 |
-
hf_hub_download(repo_id="bartowski/Meta-Llama-3-70B-Instruct-GGUF", filename="Meta-Llama-3-70B-Instruct-
|
11 |
|
12 |
@spaces.GPU(duration=120)
|
13 |
def respond(
|
@@ -26,7 +26,7 @@ def respond(
|
|
26 |
from llama_cpp_agent.chat_history.messages import Roles
|
27 |
|
28 |
llm = Llama(
|
29 |
-
model_path="models/Meta-Llama-3-70B-Instruct-
|
30 |
n_gpu_layers=81,
|
31 |
)
|
32 |
provider = LlamaCppPythonProvider(llm)
|
|
|
7 |
subprocess.run('pip install llama-cpp-python==0.2.75 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124', shell=True)
|
8 |
subprocess.run('pip install llama-cpp-agent==0.2.10', shell=True)
|
9 |
|
10 |
+
hf_hub_download(repo_id="bartowski/Meta-Llama-3-70B-Instruct-GGUF", filename="Meta-Llama-3-70B-Instruct-Q3_K_M.gguf", local_dir = "./models")
|
11 |
|
12 |
@spaces.GPU(duration=120)
|
13 |
def respond(
|
|
|
26 |
from llama_cpp_agent.chat_history.messages import Roles
|
27 |
|
28 |
llm = Llama(
|
29 |
+
model_path="models/Meta-Llama-3-70B-Instruct-Q3_K_M.gguf",
|
30 |
n_gpu_layers=81,
|
31 |
)
|
32 |
provider = LlamaCppPythonProvider(llm)
|