Model Card for Model ID

LoRA weights for "mistralai_Mistral-7B-Instruct-v0.2"

Model Description

Fine-tuned model to talk like middle school students, using typos/grammar errors. Trained on student Q&As physics topics such as PE/KE/LCE including pulley/ramp examples.

Developed by: Nora T
Finetuned from model: mistralai_Mistral-7B-Instruct-v0.2

Additional Sources

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

How to Get Started:

Load Mistral model first:

from peft import PeftModel # for fine-tuning
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, GenerationConfig, GPTQConfig, BitsAndBytesConfig

model_name_or_path = "mistralai/Mistral-7B-Instruct-v0.2"
nf4_config = BitsAndBytesConfig( # quantization 4-bit
   load_in_4bit=True,
   bnb_4bit_quant_type="nf4",
   bnb_4bit_use_double_quant=True,
   bnb_4bit_compute_dtype=torch.bfloat16
)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             quantization_config=nf4_config,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

Load in LoRA weights:

lora_model_path = "{path_to_loras_folder}/mistralai_Mistral-7B-Instruct-v0.2-testgen-LoRAs" # load loras
model = PeftModel.from_pretrained(
        model, lora_model_path, torch_dtype=torch.float16, force_download=True,
      )

Direct Use

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Training Hyperparams

LoRA Rank: 128
LoRA Alpha: 32
Batch Size: 64
Cutoff Length: 256
Learning rate: 3e-4
Epochs: 4
LoRA Dropout: 0.05

Training Data

Trained on raw text file

Training Procedure

Trained using an open-source web-ui:

https://github.com/oobabooga/text-generation-webui

Training Hyperparameters

Training regime: [More Information Needed]

Testing Data, Factors & Metrics

Model Examination [optional]

Technical Specifications [optional]

Compute Infrastructure

[More Information Needed]

Hardware Requirements