%%capture
# Installs Unsloth, Xformers (Flash Attention) and all other packages!
!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
!pip install --no-deps "xformers<0.0.26" trl peft accelerate bitsandbytes

Then you can load the model and use it as inference

python

from unsloth.chat_templates import get_chat_template

tokenizer = get_chat_template(
    tokenizer,
    chat_template = "llama-3", 
    map_eos_token = True, 
)

FastLanguageModel.for_inference(model) # Enable native 2x faster inference

schema = """Node properties: - **Question** - `favorites`: INTEGER Example: "0" - `answered`: BOOLEAN - `text`: STRING Example: "### This is: Bug ### Specifications OS: Win10" - `link`: STRING Example: "https://stackoverflow.com/questions/62224586/playg" - `createdAt`: DATE_TIME Min: 2020-06-05T16:57:19Z, Max: 2020-06-05T21:49:16Z - `title`: STRING Example: "Playground is not loading with apollo-server-lambd" - `id`: INTEGER Min: 62220505, Max: 62224586 - `upVotes`: INTEGER Example: "0" - `score`: INTEGER Example: "-1" - `downVotes`: INTEGER Example: "1" - **Tag** - `name`: STRING Example: "aws-lambda" - **User** - `image`: STRING Example: "https://lh3.googleusercontent.com/-NcFYSuXU0nk/AAA" - `link`: STRING Example: "https://stackoverflow.com/users/10251021/alexandre" - `id`: INTEGER Min: 751, Max: 13681006 - `reputation`: INTEGER Min: 1, Max: 420137 - `display_name`: STRING Example: "Alexandre Le" Relationship properties: The relationships: (:Question)-[:TAGGED]->(:Tag) (:User)-[:ASKED]->(:Question)"""
question = "Identify the top 5 questions with the most downVotes."

messages = [
      {"role": "system", "content": "Given an input question, convert it to a Cypher query. No pre-amble."},
      {"role": "user", "content": f"""Based on the Neo4j graph schema below, write a Cypher query that would answer the user's question:
{schema}

Question: {question}
Cypher query:"""}
]
inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True, # Must add for generation
    return_tensors = "pt",
).to("cuda")

outputs = model.generate(input_ids = inputs, max_new_tokens = 128, use_cache = True)
tokenizer.batch_decode(outputs)

tomasonjo/text2cypher-demo-16bit

Uploaded model

Example usage:

tomasonjo/
text2cypher-demo-16bit