Change references from 8B to 70B

README.md

@@ -22,7 +22,7 @@ tags:
 - healthcare
 pipeline_tag: question-answering
 base_model:
-- meta-llama/Llama-3.1-8B
+- meta-llama/Llama-3.1-70B
 ---
 <p align="center">
   <picture>
@@ -191,7 +191,7 @@ print(outputs[0]["generated_text"][len(prompt):])
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "HPAI-BSC/Llama31-Aloe-Beta-8B"
+model_id = "HPAI-BSC/Llama31-Aloe-Beta-70B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
@@ -351,7 +351,7 @@ To compare Aloe with the most competitive open models (both general purpose and
 
 Benchmark results indicate the training conducted on Aloe has boosted its performance achieving comparable results with SOTA models like Llama3-OpenBioLLLM, Llama3-Med42, MedPalm-2 and GPT-4. Llama31-Aloe-Beta-70B  also outperforms the other existing medical models in the OpenLLM Leaderboard and in the evaluation of other medical tasks like Medical Factualy and Medical Treatment recommendations among others. All these results make Llama31-Aloe-Beta-70B one of the best existing models for healthcare.
 
-With the help of prompting techniques the performance of Llama3-Aloe-8B-Beta is significantly improved. Medprompting in particular provides a 4% increase in reported accuracy, after which Llama31-Aloe-Beta-70B outperforms all the existing models that do not use RAG evaluation. 
+With the help of prompting techniques the performance of Llama3-Aloe-70B-Beta is significantly improved. Medprompting in particular provides a 4% increase in reported accuracy, after which Llama31-Aloe-Beta-70B outperforms all the existing models that do not use RAG evaluation. 
 
 
 ## Environmental Impact