Memorize

Fine-tuning LLM itself to memorize information using unsupervised learning.

This tool requires LLMs that support fine-tuning. Currently, only langchain.llms import GradientLLM is supported.

Imports

import os

from langchain.agents import AgentExecutor, AgentType, initialize_agent, load_tools
from langchain.chains import LLMChain
from langchain.memory import ConversationBufferMemory
from langchain_community.llms import GradientLLM

API Reference:

• AgentExecutor
• AgentType
• initialize_agent
• load_tools
• LLMChain
• ConversationBufferMemory
• GradientLLM

Set the Environment API Key

Make sure to get your API key from Gradient AI. You are given $10 in free credits to test and fine-tune different models.

from getpass import getpass

if not os.environ.get("GRADIENT_ACCESS_TOKEN", None):
    # Access token under https://auth.gradient.ai/select-workspace
    os.environ["GRADIENT_ACCESS_TOKEN"] = getpass("gradient.ai access token:")
if not os.environ.get("GRADIENT_WORKSPACE_ID", None):
    # `ID` listed in `$ gradient workspace list`
    # also displayed after login at at https://auth.gradient.ai/select-workspace
    os.environ["GRADIENT_WORKSPACE_ID"] = getpass("gradient.ai workspace id:")
if not os.environ.get("GRADIENT_MODEL_ADAPTER_ID", None):
    # `ID` listed in `$ gradient model list --workspace-id "$GRADIENT_WORKSPACE_ID"`
    os.environ["GRADIENT_MODEL_ID"] = getpass("gradient.ai model id:")

Optional: Validate your Environment variables GRADIENT_ACCESS_TOKEN and GRADIENT_WORKSPACE_ID to get currently deployed models.

Create the GradientLLM instance

You can specify different parameters such as the model name, max tokens generated, temperature, etc.

llm = GradientLLM(
    model_id=os.environ["GRADIENT_MODEL_ID"],
    # # optional: set new credentials, they default to environment variables
    # gradient_workspace_id=os.environ["GRADIENT_WORKSPACE_ID"],
    # gradient_access_token=os.environ["GRADIENT_ACCESS_TOKEN"],
)

Load tools

tools = load_tools(["memorize"], llm=llm)

Initiate the Agent

agent = initialize_agent(
    tools,
    llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
    # memory=ConversationBufferMemory(memory_key="chat_history", return_messages=True),
)

Run the agent

Ask the agent to memorize a piece of text.

agent.run(
    "Please remember the fact in detail:\nWith astonishing dexterity, Zara Tubikova set a world record by solving a 4x4 Rubik's Cube variation blindfolded in under 20 seconds, employing only their feet."
)

> Entering new AgentExecutor chain...
I should memorize this fact.
Action: Memorize
Action Input: Zara T
Observation: Train complete. Loss: 1.6853971333333335
Thought:I now know the final answer.
Final Answer: Zara Tubikova set a world

> Finished chain.

'Zara Tubikova set a world'