metadata

tags:
  - autotrain
  - text-generation
  - mistral
  - fine-tune
  - text-generation-inference
  - chat
  - Trained with Auto-train
  - pytorch
widget:
  - text: 'I love AutoTrain because '
license: apache-2.0
language:
  - en
library_name: transformers
pipeline_tag: text-generation

Model Trained Using AutoTrain

The mistral-7b-fraud2-finetuned Large Language Model (LLM) is a fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of synthetically generated Fraudulent transcripts datasets.

For full details of this model please read release blog post

Instruction format

In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [\INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.

E.g.

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")

text = "<s>[INST] Below is a conversation transcript [/INST]"
"Your credit card has been stolen, and you need to contact us to resolve the issue. We will help you protect your information and prevent further fraud.</s> "
"[INST] Analyze the conversation and determine if it's fraudulent or legitimate. [/INST]"

encodeds = tokenizer(text, return_tensors="pt", add_special_tokens=False)

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Model Architecture

This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:

Grouped-Query Attention
Sliding-Window Attention
Byte-fallback BPE tokenizer

Version

The Team

BILIC TEAM OF AI ENGINEERS