Name: Yi 6B
Author: 01-ai

Yi 6B is an open-source language model by 01-ai. Features: 6b LLM, VRAM: 12.1GB, Context: 4K, License: apache-2.0, HF Score: 54, LLM Explorer Score: 0.23, Arc: 83.8, HellaSwag: 73.1, MMLU: 64, TruthfulQA: 41.9, WinoGrande: 73.8, GSM8K: 39.9.

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

Model Card on HF 🤗: https://huggingface.co/01-ai/Yi-6B

Yi 6B Benchmarks

IFEval: 28.93 vs 88 (so35)^-67.1%

ARC: 83.8 vs 96.7 (so35)^-13.3%

HellaSwag: 73.1 vs 95.3 (gpt4)^-23.3%

MMLU: 64 vs 88.3 (so35)^-27.5%

TruthfulQA: 41.86 vs 59 (gpt4)^-29.1%

WinoGrande: 73.8 vs 87.5 (gpt4)^-15.7%

GSM8K: 39.9 vs 96.4 (so35)^-58.6%

OpenCompas: 51.5 vs 73.3 (gpt4)^-29.7%

Exam: 66.8 vs 77.2 (gpt4)^-13.5%

Language: 37.3 vs 62 (gpt4)^-39.8%

Knowledge: 49.4 vs 73.5 (gpt4)^-32.8%

Understand: 70 vs 70 (gpt4)^0%

Reasoning: 45.2 vs 74.4 (gpt4)^-39.2%

MATH Lvl 5: 1.59

LLME Score: 0.22712

^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)

🌟 Advertise your project 🚀

Yi 6B Parameters and Internals

Model Type

text generation, chat

Use Cases

Areas:

research, commercial applications, personal use

Primary Use Cases:

text and chat generation

Limitations:

May produce hallucinations, Non-determinism in re-generation, Cumulative error potential

Considerations:

Adjust generation parameters for diverse responses

Additional Notes

Yi is based on Llama architecture but not a derivative; independently trained.

Supported Languages

English (high), Chinese (high)

Training Details

Data Sources:

multilingual corpus, custom datasets developed by Yi

Data Volume:

3T tokens

Methodology:

Supervised Fine-Tuning (SFT) for chat models

Context Length:

200000

Training Time:

unknown

Hardware Used:

NVIDIA A800, GPU environment

Model Architecture:

Transformer-based, similar to Llama

Responsible Ai Considerations

Fairness:

Not detailed

Transparency:

Open-source distribution under Apache 2.0

Accountability:

Not specified

Mitigation Strategies:

Uses compliance checking algorithms to maximize data compliance

Input Output

Input Format:

Text input for prompts

Accepted Modalities:

text

Output Format:

Generated text output

Performance Tips:

Use appropriate generation settings (temperature, top_p) for task diversity

Release Notes

Version:

Yi 1.5

Date:

2024-05-13

Notes:

Improved coding, math, reasoning abilities

LLM Name	Yi 6B
Repository 🤗	https://huggingface.co/01-ai/Yi-6B
Model Size	6b
Required VRAM	12.1 GB
Updated	2026-04-10
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	14	712	2 GB
Yi 6B AWQ	1	12	3 GB
Yi 6B GPTQ	1	4	3 GB
... Spicyboros 3.1 4.0bpw H6 EXL2	3	6	3 GB
... Spicyboros 3.1 3.0bpw H6 EXL2	1	2	2 GB

Best Alternatives to Yi 6B

Best Alternatives	Context / RAM	Downloads	Likes
Yi 6B 200K	195K / 12.1 GB	16831	172
Yi 6B 200K AEZAKMI V2	195K / 12.1 GB	584	1
Yi 6B 200K DPO	195K / 12.1 GB	691	0
Wukong Yi 6B 200K	195K / 12.1 GB	5	1
Barcenas 6B 200K	195K / 12.1 GB	1848	2
Yi 6B 200K Llamafied	195K / 12.1 GB	10	11
Yi 6B 200K Llama	195K / 12.1 GB	4	5
Llama 3.2 6B AlgoCode	128K / 12.7 GB	23	1
Chatglm2 6B Port Llama	32K / 12.5 GB	5	4
Miqu 6B Truthy	31K / 11.3 GB	109	1

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? 52721 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.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Yi 6B by 01-ai

» All LLMs » 01-ai » Yi 6B URL Share it on