Update app.py
Browse files
app.py
CHANGED
|
@@ -46,7 +46,7 @@ whisper_model = WhisperModel("large-v3", device="cuda", compute_type="float16")
|
|
| 46 |
|
| 47 |
# Load Saul-Instruct-v1-GGUF.Q4_K_M
|
| 48 |
print("Loading Saul-Instruct-v1-GGUF.Q4_K_M")
|
| 49 |
-
hf_hub_download(repo_id="
|
| 50 |
saul_model_path="./Saul-Instruct-v1.Q4_K_M.gguf"
|
| 51 |
saul_instruct_llm = Llama(model_path=saul_model_path,n_gpu_layers=35,max_new_tokens=256, context_window=16384, n_ctx=16384, n_batch=128,verbose=False)
|
| 52 |
|
|
|
|
| 46 |
|
| 47 |
# Load Saul-Instruct-v1-GGUF.Q4_K_M
|
| 48 |
print("Loading Saul-Instruct-v1-GGUF.Q4_K_M")
|
| 49 |
+
hf_hub_download(repo_id="TheBloke/Wizard-Vicuna-30B-Uncensored-GGUF", local_dir=".", filename="Wizard-Vicuna-30B-Uncensored.Q4_K_M.gguf")
|
| 50 |
saul_model_path="./Saul-Instruct-v1.Q4_K_M.gguf"
|
| 51 |
saul_instruct_llm = Llama(model_path=saul_model_path,n_gpu_layers=35,max_new_tokens=256, context_window=16384, n_ctx=16384, n_batch=128,verbose=False)
|
| 52 |
|