nmitchko/medfalcon-v2-40b-lora

MedFalcon v2 40b LoRA - Final

Model Description

This a model release at 1 epoch. For evaluation use only! Limitations:

• Do not use to treat patients! Treat AI content as if you wrote it!!!

Architecture

nmitchko/medfalcon-v2-40b-lora is a large language model LoRa specifically fine-tuned for medical domain tasks. It is based on Falcon-40b at 40 billion parameters.

The primary goal of this model is to improve question-answering and medical dialogue tasks. It was trained using LoRA, specifically QLora, to reduce memory footprint.

See Training Parameters for more info This Lora supports 4-bit and 8-bit modes.

Requirements

bitsandbytes>=0.39.0
peft
transformers

Steps to load this model:

1. Load base model using transformers
2. Apply LoRA using peft

# 
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
from peft import PeftModel

model = "tiiuae/falcon-40b"
LoRA = "nmitchko/medfalcon-v2-40b-lora"

# If you want 8 or 4 bit set the appropriate flags
load_8bit = True

tokenizer = AutoTokenizer.from_pretrained(model)

model = AutoModelForCausalLM.from_pretrained(model,
    load_in_8bit=load_8bit,
    torch_dtype=torch.float16,
    trust_remote_code=True,
)

model = PeftModel.from_pretrained(model, LoRA)

pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
)

sequences = pipeline(
   "What does the drug ceftrioxone do?\nDoctor:",
    max_length=200,
    do_sample=True,
    top_k=40,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)

for seq in sequences:
    print(f"Result: {seq['generated_text']}")

Training Parameters

The model was trained for or 1 epoch on a custom, unreleased dataset named medconcat. medconcat contains only human generated content and weighs in at over 100MiB of raw text.

Item	Amount	Units
LoRA Rank	64	~
LoRA Alpha	16	~
Learning Rate	1e-4	SI
Dropout	5	%