Model does not response
Hi i am trying to use this model with llama.cpp and langchain, however the model just does not response why.
llm = LlamaCpp(
model_path="/content/openbuddy-llama2-13b-v11.1.Q5_K_M.gguf",
n_gpu_layers=n_gpu_layers,
n_batch=n_batch,
callback_manager=callback_manager,
temperature=0.7,
n_ctx=4096,
verbose=True, # Verbose is required to pass to the callback manager
)
memory = ConversationBufferWindowMemory(
memory_key="chat_history", return_messages=True
)
First try:
llm("Who are you?")
output: "\n"
Second Try:
template = """system: You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
You can speak fluently in many languages, for example: English, Chinese.
You cannot access the internet, but you have vast knowledge, cutoff: 2021-09.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.
user: {human_input}
assistant:
"""
prompt = PromptTemplate(template=template, input_variables=["human_input"])
llm_chain = LLMChain(llm=llm, prompt=prompt, verbose=True)
llm_chain.run(human_input="How are you?")
Output:
Entering new LLMChain chain...
Prompt after formatting:
system: You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
You can speak fluently in many languages, for example: English, Chinese.
You cannot access the internet, but you have vast knowledge, cutoff: 2021-09.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.
user: How are you?
assistant:
Llama.generate: prefix-match hit
Finished chain.