Bllossom
/

llama-3-Korean-Bllossom-70B-gguf-Q4_K_M

Inference Endpoints

Model card Files Files and versions Community

limhyeonseok commited on May 14

Commit

746d06c

•

1 Parent(s): 28666fd

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -95,7 +95,7 @@ from transformers import AutoTokenizer
 model_id = 'Bllossom/llama-3-Korean-Bllossom-70B-gguf-Q4_K_M'
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = Llama(
-    model_path='YOUR-LOCAL-FOLDER-PATH/llama-3-Korean-Bllossom-70B-RAG-gguf-Q4_K_M.gguf',
     n_ctx=512,
     n_gpu_layers=-1        # Number of model layers to offload to GPU
 )

 model_id = 'Bllossom/llama-3-Korean-Bllossom-70B-gguf-Q4_K_M'
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = Llama(
+    model_path='YOUR-LOCAL-FOLDER-PATH/llama-3-Korean-Bllossom-70B-gguf-Q4_K_M.gguf',
     n_ctx=512,
     n_gpu_layers=-1        # Number of model layers to offload to GPU
 )