Hugging Face's logo

adriata
/
med_mistral

Text Generation
Transformers
Safetensors
mistral
trl
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
med_mistral / README.md
adriata's picture
adriata
Update README.md
d3b9cd1 verified
preview code
|
raw
history blame contribute delete
3.01 kB
metadata
license: apache-2.0
library_name: transformers
tags:
  - trl
  - sft
datasets:
  - pubmed
  - bigbio/czi_drsm
  - bigbio/bc5cdr
  - bigbio/distemist
  - pubmed_qa
  - medmcqa

Model Card for med_mistral

Model Details

Model Description

Model Mistral-7B-Instruct-v0.2 finetuned with QLoRA on multiple medical datasets.

4-bit version: med_mistral_4bit

  • License: apache-2.0
  • Finetuned from model : mistralai/Mistral-7B-Instruct-v0.2

Model Sources [optional]

Uses

The model is finetuned on medical data and is intended only for research. It should not be used as a substitute for professional medical advice, diagnosis, or treatment.

Bias, Risks, and Limitations

The model's predictions are based on the information available in the finetuned medical dataset. It may not generalize well to all medical conditions or diverse patient populations.

Sensitivity to variations in input data and potential biases present in the training data may impact the model's performance.

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.

How to Get Started with the Model

Use the code below to get started with the model.

# !pip install -q transformers accelerate bitsandbytes

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adriata/med_mistral")
model = AutoModelForCausalLM.from_pretrained("adriata/med_mistral")

prompt_template = """<s>[INST] {prompt} [/INST]"""

prompt = "What is influenza?"

model_inputs = tokenizer.encode(prompt_template.format(prompt=prompt),
                                return_tensors="pt").to("cuda")

generated_ids = model.generate(model_inputs, max_new_tokens=512, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Training Details

~13h - 20k examples x 1 epoch

GPU: OVH - 1 × NVIDIA TESLA V100S (32 GiB RAM)

Training Data

Training data included 20k examples randomly selected from datasets:

  • pubmed
  • bigbio/czi_drsm
  • bigbio/bc5cdr
  • bigbio/distemist
  • pubmed_qa
  • medmcqa