Aurora Nights 70B V1.0 By sophosympatheia: Benchmarks, Features and Detailed Analysis. Insights on Aurora Nights 70B V1.0.

Arxiv:2307.11760 Autotrain compatible En Endpoints compatible Llama Model-index Region:us Safetensors Sharded Tensorflow

Aurora Nights 70B V1.0 Benchmarks

ARC: 71.33^-25.9%

HellaSwag: 88.33^-7.3%

MMLU: 70.47^-18.5%

TruthfulQA: 62.81^6.5%

WinoGrande: 83.35^-4.7%

GSM8K: 66.34^-27.9%

^nn.n% — How the model compares to the GPT-4.

Aurora Nights 70B V1.0 Parameters and Internals

LLM Name	Aurora Nights 70B V1.0
Repository	Open on 🤗
Model Size	70b
Required VRAM	137.8 GB
Updated	2024-07-27
Maintainer	sophosympatheia
Model Type	llama
Model Files	8.1 GB: 1-of-17 8.1 GB: 2-of-17 8.2 GB: 3-of-17 8.1 GB: 4-of-17 8.1 GB: 5-of-17 8.1 GB: 6-of-17 8.2 GB: 7-of-17 8.1 GB: 8-of-17 8.1 GB: 9-of-17 8.1 GB: 10-of-17 8.2 GB: 11-of-17 8.1 GB: 12-of-17 8.1 GB: 13-of-17 8.1 GB: 14-of-17 8.2 GB: 15-of-17 8.1 GB: 16-of-17 7.8 GB: 17-of-17
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.1
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Aurora Nights 70B V1.0 (sophosympatheia/Aurora-Nights-70B-v1.0)

Quantized Models of the Aurora Nights 70B V1.0

Model	Likes	Downloads	VRAM
Aurora Nights 70B V1.0 GGUF	8	169	29 GB
Aurora Nights 70B V1.0 GPTQ	1	41	35 GB
Aurora Nights 70B V1.0 AWQ	3	8	36 GB

Best Alternatives to Aurora Nights 70B V1.0

Best Alternatives	HF Rank	Context/RAM	Downloads	Likes
... 3 70B Instruct Gradient 1048K	0.3	1024K / 141.9 GB	2794	114
... Chat 1048K Chinese Llama3 70B	0.3	1024K / 141.9 GB	2790	5
Llama3 Function Calling 1048K	0.2	1024K / 141.9 GB	11	1
...a 3 70B Instruct Gradient 524K	0.3	512K / 141.9 GB	444	22
...a 3 70B Instruct Gradient 262K	0.3	256K / 141.9 GB	1637	54
...ama 3 70B Arimas Story RP V2.0	0.3	256K / 141.1 GB	171	3
...ama 3 70B Arimas Story RP V1.5	0.3	256K / 141.2 GB	170	2
...ama 3 70B Arimas Story RP V1.6	0.2	256K / 141.2 GB	16	0
Yi 70B 200K RPMerge Franken	0.2	195K / 142.4 GB	10	1
...3.1 70B Japanese Instruct 2407	0.4	128K / 141.9 GB	38	23

Note: green Score (e.g. "73.2") means that the model is better than sophosympatheia/Aurora-Nights-70B-v1.0.

Rank the Aurora Nights 70B V1.0 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? 34447 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 v2024072501

Support LLM Explorer