Yi 9B By 01-ai: Benchmarks, Features and Detailed Analysis. Insights on Yi 9B.

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

Model Card on HF 🤗: https://huggingface.co/01-ai/Yi-9B

Yi 9B Benchmarks

MMLU Pro: 28.6

GPQA: 9.06

MUSR: 8.91

BBH: 27.63

IFEval: 27.09 vs 88 (so35)^-69.2%

ARC: 61.18 vs 96.7 (so35)^-36.7%

HellaSwag: 78.82 vs 95.3 (gpt4)^-17.3%

MMLU: 70.06 vs 88.3 (so35)^-20.7%

TruthfulQA: 42.45 vs 59 (gpt4)^-28.1%

WinoGrande: 77.51 vs 87.5 (gpt4)^-11.4%

GSM8K: 48.98 vs 96.4 (so35)^-49.2%

MATH Lvl 5: 5.59

LLME Score: 0.26156

^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 9B 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 9B
Repository 🤗	https://huggingface.co/01-ai/Yi-9B
Model Size	9b
Required VRAM	17.6 GB
Updated	2025-09-08
Maintainer	01-ai
Model Type	llama
Model Files	9.9 GB: 1-of-2 7.7 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Quantized Models of the Yi 9B

Model	Likes	Downloads	VRAM
Yi 9B GGUF	16	139	3 GB

Best Alternatives to Yi 9B

Best Alternatives	Context / RAM	Downloads	Likes
Yi 9B 200K	256K / 17.7 GB	12516	77
Xgen Small 9B Instruct R	256K / 42.5 GB	1165	7
SekhmetX 9B V0.1 Test	256K / 21.2 GB	71	2
SekmetX 9B V0.1 Test	256K / 21.2 GB	69	2
Mike Hawk 9B	256K / 21.3 GB	9	3
Austral Xgen 9B Winton	256K / 21.3 GB	10	2
...rce Xgen Small 9B Rebased V0.1	256K / 42.5 GB	17	0
...rce Xgen Small 9B Rebased V0.1	256K / 42.5 GB	14	0
Xgen Small 9B Base R	256K / 42.5 GB	73	2
BigYi 15.75B 200K	256K / 30.3 GB	5	0

Rank the Yi 9B 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? 51187 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 v20241124

Support LLM Explorer