Hugging Face's logo

Zoyd
/
01-ai_Yi-1.5-9B-32K-3_0bpw_exl2

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
3-bit
exl2
Model card Files Community
01-ai_Yi-1.5-9B-32K-3_0bpw_exl2 / README.md
Zoyd's picture
Zoyd
Upload folder using huggingface_hub
32a142e verified
preview code
|
raw
history blame contribute delete
6.81 kB
metadata
license: apache-2.0

Exllamav2 quant (exl2 / 3.0 bpw) made with ExLlamaV2 v0.0.21

Other EXL2 quants:

Quant Model Size lm_head
2.2
2900 MB
6
2.5
3173 MB
6
3.0
3667 MB
6
3.5
4162 MB
6
3.75
4410 MB
6
4.0
4658 MB
6
4.25
4906 MB
6
5.0
5647 MB
6
6.0
6686 MB
8
6.5
7184 MB
8
8.0
8200 MB
8

🐙 GitHub • 👾 Discord • 🐤 Twitter • 💬 WeChat
📝 Paper • 🙌 FAQ • 📗 Learning Hub

Intro

Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.

Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.

Model Context Length Pre-trained Tokens
Yi-1.5 4K, 16K, 32K 3.6T

Models

Benchmarks

  • Chat models

    Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.

    image/png

    Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.

    image/png

  • Base models

    Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.

    image/png

    Yi-1.5-9B is the top performer among similarly sized open-source models.

    image/png

Quick Start

For getting up and running with Yi-1.5 models quickly, see README.