Downloads · 30 days
48
1% of all-time downloads
RichardErkhov/Nexusflow_-_Athene-70B-gguf
Nexusflow_-_Athene-70B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
48
1% of all-time downloads
All-time downloads
5.6K
Public
Repo size
799 GB
Likes
0
Public
Click a slice to open those files.
.gguf926 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Athene-70B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Athene-70B.Q2_K.gguf | Q2_K | 24.56GB |
| Athene-70B.IQ3_XS.gguf | IQ3_XS | 27.29GB |
| Athene-70B.IQ3_S.gguf | IQ3_S | 28.79GB |
| Athene-70B.Q3_K_S.gguf | Q3_K_S | 28.79GB |
| Athene-70B.IQ3_M.gguf | IQ3_M | 29.74GB |
| Athene-70B.Q3_K.gguf | Q3_K | 31.91GB |
| Athene-70B.Q3_K_M.gguf | Q3_K_M | 31.91GB |
| Athene-70B.Q3_K_L.gguf | Q3_K_L | 34.59GB |
| Athene-70B.IQ4_XS.gguf | IQ4_XS | 35.64GB |
| Athene-70B.Q4_0.gguf | Q4_0 | 37.22GB |
| Athene-70B.IQ4_NL.gguf | IQ4_NL | 37.58GB |
| Athene-70B.Q4_K_S.gguf | Q4_K_S | 37.58GB |
| Athene-70B.Q4_K.gguf | Q4_K | 39.6GB |
| Athene-70B.Q4_K_M.gguf | Q4_K_M | 39.6GB |
| Athene-70B.Q4_1.gguf | Q4_1 | 41.27GB |
| Athene-70B.Q5_0.gguf | Q5_0 | 45.32GB |
| Athene-70B.Q5_K_S.gguf | Q5_K_S | 45.32GB |
| Athene-70B.Q5_K.gguf | Q5_K | 46.52GB |
| Athene-70B.Q5_K_M.gguf | Q5_K_M | 46.52GB |
| Athene-70B.Q5_1.gguf | Q5_1 | 49.36GB |
| Athene-70B.Q6_K.gguf | Q6_K | 53.91GB |
| Athene-70B.Q8_0.gguf | Q8_0 | 69.83GB |
license: other language:
We introduce Llama3-Athene-70B, an open-weights LLM trained through RLHF based off Llama-3-70B-Instruct. Athene-70B achieves a high score on Arena-Hard-Auto, a proxy benchmark for Chatbot Arena.
| Model | Arena-Hard |
|---|---|
| Claude-3.5-Sonnet (Proprietary) | 79.3% |
| GPT-4o (Proprietary) | 79.2% |
| Athene-70B (Open) | 77.8% |
| Gemini-Pro-1.5 (Proprietary) | 72.0% |
| Gemma-2-27B (Open) | 57.0% |
| Llama-3-70B (Open) | 46.6% |
Athene-70B uses the same chat template as Llama-3-70B-Instruct. Below is an example simple usage using the Transformers library.
import transformers
import torch
model_id = "Nexusflow/Athene-70B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
messages = [
{"role": "system", "content": "You are an Athene Noctura, you can only speak with owl sounds. Whoooo whooo."},
{"role": "user", "content": "Whooo are you?"},
]
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|end_of_text|>")
]
outputs = pipeline(
messages,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][-1])
We would like to thank the LMSYS Organization for their support of testing the model. We would like to thank Meta AI and the open source community for their efforts in providing the datasets and base models.
@misc{Athene2024,
title = {Athene-70B: Redefining the Boundaries of Post-Training for Open Models},
url = {https://nexusflow.ai/blogs/athene},
author = {Frick, Evan and Jin, Peter and Li, Tianle and Ganesan, Karthik and Zhang, Jian and Jiao, Jiantao and Zhu, Banghua},
month = {July},
year = {2024}
}