metadata

library_name: peft
license: apache-2.0
datasets:
  - dltdojo/ecommerce-faq-chatbot-dataset
language:
  - en
pipeline_tag: text-generation
tags:
  - text-generation-inference

Falcon 7B LLM Fine Tune Model

Model description

This model is a fine-tuned version of the tiiuae/falcon-7b model using the QLoRa library and the PEFT library. It was fine-tuned on the Ecommerce-FAQ-Chatbot-Dataset from Kaggle.

Intended uses & limitations

How to use

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch

model_id = "hipnologo/Falcon-7B-FineTune-Chatbot"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

# generate text
input_prompt = "Hello, Bot!"
input_ids = tokenizer.encode(input_prompt, return_tensors='pt')
output = model.generate(input_ids)
output_text = tokenizer.decode(output[:, input_ids.shape[-1]:][0], skip_special_tokens=True)

Training procedure

The model was fine-tuned on the Ecommerce-FAQ-Chatbot-Dataset using the bitsandbytes quantization config:

load_in_8bit: False
load_in_4bit: True
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: True
bnb_4bit_compute_dtype: bfloat16

Framework versions

PEFT 0.4.0.dev0

Evaluation results

The model was trained for 80 steps, with the training loss decreasing from 0.184 to nearly 0. The final training loss was 0.03094411873175886.

Trainable params: 2359296
All params: 3611104128
Trainable%: 0.06533447711203746

License

This model is licensed under Apache 2.0. Please see the LICENSE for more information.