Yi 6B By 01-ai: Benchmarks, Features and Detailed Analysis. Insights on Yi 6B.

Arxiv:2311.16502 Arxiv:2401.11944 Arxiv:2403.04652 Autotrain compatible Endpoints compatible Llama Pytorch Region:us Safetensors Sharded Tensorflow

Yi 6B Benchmarks

ARC: 83.8^-13%

HellaSwag: 73.1^-23.3%

MMLU: 64^-26%

TruthfulQA: 41.86^-29.1%

WinoGrande: 73.8^-15.7%

GSM8K: 39.9^-56.6%

OpenCompass Avg: 51.5 vs 73.3 (GPT-4) ^-29.7%

Exam: 66.8^-13.5%

Language: 37.3^-39.8%

Knowledge: 49.4^-32.8%

Understanding: 70^0%

Reasoning: 45.2^-39.2%

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

Yi 6B Parameters and Internals

LLM Name	Yi 6B
Repository	Open on 🤗
Model Size	6b
Required VRAM	12.1 GB
Updated	2024-07-27
Maintainer	01-ai
Model Type	llama
Model Files	9.9 GB: 1-of-2 2.2 GB: 2-of-2 9.9 GB: 1-of-2 2.2 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.34.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Quantized Models of the Yi 6B

Model	Likes	Downloads	VRAM
Yi 6B GGUF	13	517	2 GB
Yi 6B GPTQ	1	14	3 GB
Yi 6B AWQ	1	12	3 GB
... Spicyboros 3.1 4.0bpw H6 EXL2	3	14	3 GB
... Spicyboros 3.1 3.0bpw H6 EXL2	1	8	2 GB

Best Alternatives to Yi 6B

Best Alternatives	HF Rank	Context/RAM	Downloads	Likes
Yi 6B 200K	0.3	195K / 12.1 GB	6139	173
Wukong Yi 6B 200K	0.2	195K / 12.1 GB	4	1
Yi 6B 200K AEZAKMI V2	0.2	195K / 12.1 GB	925	1
Yi 6B 200K DPO	0.2	195K / 12.1 GB	952	0
Barcenas 6B 200K	0.2	195K / 12.1 GB	941	2
Yi 6B 200K Llamafied	0.2	195K / 12.1 GB	11	11
Yi 6B 200K Llama	0.2	195K / 12.1 GB	7	5
Chatglm2 6B Port Llama	0.2	32K / 12.5 GB	7	4
Miqu 6B Truthy	0.3	31K / 11.3 GB	296	1
Llama 3 6B V0.1	0.3	8K / 12.6 GB	283	12

Rank the Yi 6B 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