# chat_engine = index.as_chat_engine()
chat_engine = index.as_chat_engine(
chat_mode="context",
memory=memory,
system_prompt=system_prompt,
service_context=service_context
)
response = chat_engine.chat("Tell me a joke.")
print(f"Agent: {response}")Setting `pad_token_id` to `eos_token_id`:0 for open-end generation. A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set `padding_side='left'` when initializing the tokenizer.
ValueError: shapes (384,) and (1536,) not aligned: 384 (dim 0) != 1536 (dim 0)set_global_tokenizer(
AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf").encode
)
llm = HuggingFaceLLM(
context_window=4096,
max_new_tokens=256,
generate_kwargs={"temperature": 0.7, "do_sample": False},
system_prompt=system_prompt,
query_wrapper_prompt=query_wrapper_prompt,
tokenizer_name="StabilityAI/stablelm-tuned-alpha-3b",
model_name="StabilityAI/stablelm-tuned-alpha-3b",#hbacard/Nous-Hermes-Llama2-13b-GGUF
device_map="auto",
stopping_ids=[50278, 50279, 50277, 1, 0],
tokenizer_kwargs={"max_length": 4096},
# uncomment this if using CUDA to reduce memory usage
# model_kwargs={"torch_dtype": torch.float16}
)
# use Huggingface embeddings
from llama_index.embeddings import HuggingFaceEmbedding
# intfloat/e5-mistral-7b-instruct
# BAAI/bge-small-en-v1.5
# BAAI/bge-large-en-v1.5
embed_model = HuggingFaceEmbedding(model_name="intfloat/e5-mistral-7b-instruct")
service_context = ServiceContext.from_defaults(
chunk_size=1024,
llm=llm,
embed_model=embed_model
)
set_global_service_context(service_context)
)import torch print(torch.cuda.is_available())`
llm has to use the same embedding as the embed_model but here you are using something different "intfloat/e5-mistral-7b-instruct". Would you mind sharing how to know if two different model's embedding are compatible? Thank you!