ArvindSharma18/Phi-3-mini-4k-instruct-bnb-4bit-Clinical-Trail-Merged

Note

• This is an Experiment to generate Clinical Report Information given some of the attributes which I have trained on. Will be making a better one Soon! Stay Updated
• LORA: ArvindSharma18/Phi-3-mini-4k-instruct-bnb-4bit-Clinical-Trail

How to Use

Note: EOS issue. Will keep on Generating Secondary Outcomes.

from unsloth import FastLanguageModel
import torch
max_seq_length = 4096 
dtype = torch.float16
load_in_4bit = True

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "ArvindSharma18/Phi-3-mini-4k-instruct-bnb-4bit-Clinical-Trail-Merged",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit
)
FastLanguageModel.for_inference(model)
inputs = tokenizer(
[
    "Official Title: Randomized Trial of Usual Care vs. Specialized, Phase-specific Care for Youth at Risk for Psychosis"
], return_tensors = "pt").to("cuda")
from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer, skip_prompt = True)
_ = model.generate(input_ids = inputs.input_ids, attention_mask = inputs.attention_mask,
                   streamer = text_streamer, max_new_tokens = 2048, pad_token_id = tokenizer.eos_token_id)

Uploaded model

• Developed by: ArvindSharma18
• Finetuned from model : unsloth/Phi-3-mini-4k-instruct-bnb-4bit

This model was trained 2x faster with Unsloth and Huggingface's TRL library.