Upload folder using huggingface_hub

Test_RAG.py

@@ -60,7 +60,7 @@ if not text_example_cn_path.exists():
         f.write(content.read())
 
 model_language = "English"
-llm_model_id= "llama-3.2-3b-instruct"                          #"llama-3-8b-instruct"
+llm_model_id = "llama-3-8b-instruct"                                                #"llama-3.2-3b-instruct"                          #"llama-3-8b-instruct"
 llm_model_configuration = SUPPORTED_LLM_MODELS[model_language][llm_model_id]
 print(f"Selected LLM model {llm_model_id}")
 prepare_int4_model = True   # Prepare INT4 model
@@ -291,7 +291,8 @@ if llm_model_id == "red-pajama-3b-chat" and "GPU" in core.available_devices and
     ov_config["INFERENCE_PRECISION_HINT"] = "f32"
 
 llm = HuggingFacePipeline.from_model_id(
-    model_id="meta-llama/Llama-3.2-3B-Instruct",                                      #“meta-llama/Meta-Llama-3-8B"
+    model_id= "meta-llama/Meta-Llama-3-8B"                                                                         
+    #meta-llama/Meta-Llama-3-8B------------/meta-llama/Llama-3.2-3B-Instruct   
     task="text-generation",
     backend="openvino",
     model_kwargs={
@@ -301,14 +302,14 @@ llm = HuggingFacePipeline.from_model_id(
     },
     pipeline_kwargs={"max_new_tokens": 2},
 )
-# 设置 pad_token_id 为 eos_token_id
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-tokenizer = AutoTokenizer.from_pretrained('meta-llama/Llama-3.2-3B-Instruct')
-if tokenizer.pad_token_id is None:
-    tokenizer.pad_token_id = tokenizer.eos_token_id
-# # 同时确保 HuggingFacePipeline 使用的 tokenizer 也设置了 pad_token_id
-llm.pipeline.tokenizer.pad_token_id = tokenizer.pad_token_id
-# llm.invoke("2 + 2 =")
+# # 设置 pad_token_id 为 eos_token_id
+# from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+# tokenizer = AutoTokenizer.from_pretrained('meta-llama/Llama-3.2-3B-Instruct')
+# if tokenizer.pad_token_id is None:
+#     tokenizer.pad_token_id = tokenizer.eos_token_id
+# # # 同时确保 HuggingFacePipeline 使用的 tokenizer 也设置了 pad_token_id
+# llm.pipeline.tokenizer.pad_token_id = tokenizer.pad_token_id
+llm.invoke("2 + 2 =")
 import re
 from typing import List
 from langchain.text_splitter import (