language:
- en
license: other
license_name: apachelabs-community-license
license_link: LICENSE.md
tags:
- Llama-3
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
- function calling
- json mode
- axolotl
- roleplaying
- chat
base_model: meta-llama/Meta-Llama-3.1-70B
library_name: transformers
extra_gated_prompt: >-
By accessing this model, you agree to the terms of use as outlined in the
Apache Labs Community License and confirm that you will not use the model in
ways that violate ethical guidelines.
extra_gated_fields:
Name: text
Email: text
Country: country
Birthday: date_picker
Affiliation: text
Intended Use:
type: select
options:
- Research
- Education
- Commercial
- label: Other
value: other
Agreement to Apache Labs Community License: checkbox
Athena 3.1 70B by Apache Labs
Athena 3.1 70B is a state-of-the-art language model developed by Apache Labs, based on Meta's Llama-3.1-70B. This fine-tuned model is designed for superior natural language understanding, advanced reasoning, and coherent text generation, suitable for a variety of professional, research, and creative tasks.
Model Overview
Athena 3.1 70B leverages the robust architecture of Llama-3.1-70B, tuned for high accuracy, nuanced comprehension, and reliable performance across diverse contexts. This model excels in tasks requiring deep language processing and logical coherence, making it a valuable tool for complex applications.
Key Features
- Enhanced Contextual Understanding: Maintains consistency across longer passages, providing accurate multi-turn responses.
- Advanced Reasoning Capabilities: Tuned to handle logical reasoning and complex question answering.
- Versatile Application: Effective across tasks such as content generation, research analysis, technical writing, and more.
Quickstart Guide
To get started with Athena 3.1 70B, you can use it in a Hugging Face environment with the following setup:
Use a pipeline as a high-level helper:
from transformers import pipeline
# Define the pipeline
pipe = pipeline("text-generation", model="apache-labs/Athena-3.1-70B")
# Define a prompt
messages = [
{"role": "user", "content": "Who are you?"},
]
# Generate response
response = pipe(messages)
print(response)
Load Model Directly:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("apache-labs/Athena-3.1-70B")
model = AutoModelForCausalLM.from_pretrained("apache-labs/Athena-3.1-70B")