Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Yi-1.5-9B-Chat-16K - GGUF
- Model creator: https://huggingface.co/01-ai/
- Original model: https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Yi-1.5-9B-Chat-16K.Q2_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q2_K.gguf) | Q2_K | 3.12GB |
| [Yi-1.5-9B-Chat-16K.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.IQ3_XS.gguf) | IQ3_XS | 3.46GB |
| [Yi-1.5-9B-Chat-16K.IQ3_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.IQ3_S.gguf) | IQ3_S | 3.64GB |
| [Yi-1.5-9B-Chat-16K.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q3_K_S.gguf) | Q3_K_S | 3.63GB |
| [Yi-1.5-9B-Chat-16K.IQ3_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.IQ3_M.gguf) | IQ3_M | 3.78GB |
| [Yi-1.5-9B-Chat-16K.Q3_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q3_K.gguf) | Q3_K | 4.03GB |
| [Yi-1.5-9B-Chat-16K.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q3_K_M.gguf) | Q3_K_M | 4.03GB |
| [Yi-1.5-9B-Chat-16K.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q3_K_L.gguf) | Q3_K_L | 4.37GB |
| [Yi-1.5-9B-Chat-16K.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.IQ4_XS.gguf) | IQ4_XS | 4.5GB |
| [Yi-1.5-9B-Chat-16K.Q4_0.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q4_0.gguf) | Q4_0 | 4.69GB |
| [Yi-1.5-9B-Chat-16K.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.IQ4_NL.gguf) | IQ4_NL | 4.73GB |
| [Yi-1.5-9B-Chat-16K.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q4_K_S.gguf) | Q4_K_S | 4.72GB |
| [Yi-1.5-9B-Chat-16K.Q4_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q4_K.gguf) | Q4_K | 4.96GB |
| [Yi-1.5-9B-Chat-16K.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q4_K_M.gguf) | Q4_K_M | 4.96GB |
| [Yi-1.5-9B-Chat-16K.Q4_1.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q4_1.gguf) | Q4_1 | 5.19GB |
| [Yi-1.5-9B-Chat-16K.Q5_0.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q5_0.gguf) | Q5_0 | 5.69GB |
| [Yi-1.5-9B-Chat-16K.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q5_K_S.gguf) | Q5_K_S | 5.69GB |
| [Yi-1.5-9B-Chat-16K.Q5_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q5_K.gguf) | Q5_K | 5.83GB |
| [Yi-1.5-9B-Chat-16K.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q5_K_M.gguf) | Q5_K_M | 5.83GB |
| [Yi-1.5-9B-Chat-16K.Q5_1.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q5_1.gguf) | Q5_1 | 6.19GB |
| [Yi-1.5-9B-Chat-16K.Q6_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q6_K.gguf) | Q6_K | 6.75GB |
| [Yi-1.5-9B-Chat-16K.Q8_0.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-Chat-16K-gguf/blob/main/Yi-1.5-9B-Chat-16K.Q8_0.gguf) | Q8_0 | 8.74GB |
Original model description:
---
license: apache-2.0
---
🐙 GitHub •
👾 Discord •
🐤 Twitter •
💬 WeChat
📝 Paper •
💪 Tech Blog •
🙌 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
- Chat models
| Name | Download |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI)|
| Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
| Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
| Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
| Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
- Base models
| Name | Download |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
| Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
| Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
| Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
| Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
# Benchmarks
- Chat models
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/KcsJ9Oc1VnEmfCDEJc5cd.png)
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/xf6pLg5jqRCwjlh6m3t6_.png)
- Base models
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/BwU7QM-03dZvZzwdIE1xY.png)
Yi-1.5-9B is the top performer among similarly sized open-source models.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/y-EYSYPT-3aWLJ0x8R94F.png)
# Quick Start
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).