Vicuna 7B V1.5 16K By lmsys: Benchmarks, Features and Detailed Analysis. Insights on Vicuna 7B V1.5 16K.

Arxiv:2306.05685 Arxiv:2307.09288 Autotrain compatible Llama Pytorch Region:us Sharded

Vicuna 7B V1.5 16K Benchmarks

ARC: 72.1^-25.1%

HellaSwag: 72.4^-24%

MMLU: 49.6^-42.7%

TruthfulQA: 50.35^-14.7%

WinoGrande: 71.03^-18.8%

GSM8K: 22^-76.1%

OpenCompass Avg: 46.9 vs 73.3 (GPT-4) ^-36%

Exam: 51.5^-33.3%

Language: 35.9^-42.1%

Knowledge: 53^-27.9%

Understanding: 59^-15.7%

Reasoning: 42.7^-42.6%

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

Vicuna 7B V1.5 16K Parameters and Internals

LLM Name	Vicuna 7B V1.5 16K
Repository	Open on 🤗
Model Size	7b
Required VRAM	13.5 GB
Updated	2024-07-27
Maintainer	lmsys
Model Type	llama
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Vicuna 7B V1.5 16K (lmsys/vicuna-7b-v1.5-16k)

Quantized Models of the Vicuna 7B V1.5 16K

Model	Likes	Downloads	VRAM
Vicuna 7B V1.5 16K GGUF	9	578	2 GB
Vicuna 7B V1.5 16K AWQ	1	51	3 GB
Vicuna 7B V1.5 16K GPTQ	10	61	3 GB
Vicuna 7B V1.5 16K GGML	13	9	2 GB

Best Alternatives to Vicuna 7B V1.5 16K

Best Alternatives	HF Rank	Context/RAM	Downloads	Likes
...1M 1000000ctx AEZAKMI 3 1 1702	0.2	1024K / 13.5 GB	296	1
Yarn Llama 2 7B 128K	0.2	128K / 13.5 GB	12746	38
LLaMA 7B PoSE YaRN 128K	0.2	128K / 13.5 GB	28	2
LLaMA 7B PoSE YaRN 96K	0.2	96K / 13.5 GB	11	1
LLaMA 7B PoSE Linear 96K	0.2	96K / 27 GB	11	1
Chat Llama2 7B 80K	0.2	80K / 13.8 GB	11	0
Llama2 7B 80K	0.2	80K / 13.8 GB	8	0
Lloma Step400	0.3	64K / 13.5 GB	294	0
Lloma Step200	0.3	64K / 13.5 GB	298	0
Lloma Step50	0.2	64K / 13.5 GB	297	0

Note: green Score (e.g. "73.2") means that the model is better than lmsys/vicuna-7b-v1.5-16k.

Rank the Vicuna 7B V1.5 16K 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? 34446 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