Athena V3 By IkariDev: Benchmarks, Features and Detailed Analysis. Insights on Athena V3.

Autotrain compatible Endpoints compatible Llama Pytorch Region:us Sharded

Athena V3 Benchmarks

ARC: 61.69 vs 96.7 (so35)^-36.2%

HellaSwag: 84.34 vs 95.3 (gpt4)^-11.5%

MMLU: 57.87 vs 88.3 (so35)^-34.5%

TruthfulQA: 51.26 vs 59 (gpt4)^-13.1%

WinoGrande: 75.77 vs 87.5 (gpt4)^-13.4%

GSM8K: 11.6 vs 96.4 (so35)^-88%

LLME Score: 0.19602

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Athena V3 Parameters and Internals

LLM Name	Athena V3
Repository 🤗	https://huggingface.co/IkariDev/Athena-v3
Required VRAM	26 GB
Updated	2024-09-16
Maintainer	IkariDev
Model Type	llama
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.33.2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Quantized Models of the Athena V3

Model	Likes	Downloads	VRAM
Athena V3 GGUF	7	274	5 GB
Athena V3 GPTQ	10	12	7 GB
Athena V3 AWQ	2	8	7 GB

Best Alternatives to Athena V3

Best Alternatives	Context / RAM	Downloads	Likes
LWM Text Chat 512K	512K / 13.5 GB	11	2
LWM Text 512K	512K / 13.5 GB	6	2
LWM Text Chat 256K	256K / 13.5 GB	40	3
LWM Text 256K	256K / 13.5 GB	7	3
Pallas 0.5 LASER 0.1	195K / 68.9 GB	706	2
Cyber13	128K / 16.1 GB	66	0
Cyber8	128K / 16.1 GB	83	0
LWM Text Chat 128K	128K / 13.5 GB	11	20
...Model LWM Text Chat 128K 55bpw	128K / 4.8 GB	13	3
LWM Text 128K	128K / 13.5 GB	12	1

Note: green Score (e.g. "73.2") means that the model is better than IkariDev/Athena-v3.

Rank the Athena V3 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 35941 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Release v2024072803

Support LLM Explorer