metadata

license: apache-2.0
language:
  - en
tags:
  - text-generation
  - llama-2
  - fine-tuning
  - mindsdb
  - huggingface
base_model: meta-llama/Llama-2-7b-hf
pipeline_tag: text-generation
library_name: transformers

Llama2 Fine-tuned on MindsDB Docs

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the MindsDB documentation dataset.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "ako-oak/llama2-finetuned-mindsdb"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(**inputs, max_length=200)
    return tokenizer.decode(output[0], skip_special_tokens=True)

print(chat("What is the purpose of handlers in MindsDB?"))