persistent/text2cypher-recommendations-sft-0.5k
Viewer • Updated • 504 • 5
How to use persistent/Llama-3-8b-text2cypher-recommendations-sft-v2 with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("persistent/Llama-3-8b-text2cypher-recommendations-sft-v2", dtype="auto")How to use persistent/Llama-3-8b-text2cypher-recommendations-sft-v2 with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for persistent/Llama-3-8b-text2cypher-recommendations-sft-v2 to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for persistent/Llama-3-8b-text2cypher-recommendations-sft-v2 to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for persistent/Llama-3-8b-text2cypher-recommendations-sft-v2 to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="persistent/Llama-3-8b-text2cypher-recommendations-sft-v2",
max_seq_length=2048,
)This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
### Instruction:
You will be given a schema for Neo4j db, followed by a question.
You need to generate cypher query to fetch the relevant information
Only respond with a complete cypher query which will return the correct result
### Schema:
{}
### Question:
{}
### Cypher query:
{}<|end_of_text|>
This model is fine-tuned on 500 text2cypher synthetic dataset https://huggingface.co/datasets/persistent/text2cypher-recommendations-sft-0.5k
Base model
meta-llama/Meta-Llama-3-8B