yi-01-ai
commited on
Commit
•
faaf920
1
Parent(s):
8689e85
Auto Sync from git://github.com/01-ai/Yi.git/commit/ddfb3e80b169e48bd700177f4f896fe23e587f5a
Browse files
README.md
CHANGED
@@ -82,7 +82,7 @@ pipeline_tag: text-generation
|
|
82 |
- [Quick start](#quick-start)
|
83 |
- [Choose your path](#choose-your-parth)
|
84 |
- [pip](#pip)
|
85 |
-
- [llama.cpp](
|
86 |
- [Web demo](#web-demo)
|
87 |
- [Fine tune](#fine-tune)
|
88 |
- [Quantization](#quantization)
|
@@ -265,12 +265,12 @@ sequence length and can be extended to 32K during inference time.
|
|
265 |
- [Quick start](#quick-start)
|
266 |
- [Choose your path](#choose-your-parth)
|
267 |
- [pip](#pip)
|
268 |
-
- [llama.cpp](
|
269 |
- [Web demo](#web-demo)
|
270 |
- [Fine tune](#fine-tune)
|
271 |
- [Quantization](#quantization)
|
272 |
-
- [Deployment](
|
273 |
-
- [Learning hub](
|
274 |
|
275 |
## Quick start
|
276 |
|
@@ -280,7 +280,7 @@ Getting up and running with Yi models is simple with multiple choices available.
|
|
280 |
|
281 |
Select one of the following paths to begin your journey with Yi!
|
282 |
|
283 |
-
![Quick start - Choose your path](https://github.com/01-ai/Yi/blob/main/assets/img/quick_start_path.png)
|
284 |
|
285 |
#### 🎯 Deploy Yi locally
|
286 |
|
@@ -288,7 +288,7 @@ If you prefer to deploy Yi models locally,
|
|
288 |
|
289 |
- 🙋♀️ and you have **sufficient** resources (for example, NVIDIA A800 80GB), you can choose one of the following methods:
|
290 |
- [pip](#pip)
|
291 |
-
- [Docker](
|
292 |
- [conda-lock](https://github.com/01-ai/Yi/blob/main/docs/README_legacy.md#12-local-development-environment)
|
293 |
|
294 |
- 🙋♀️ and you have **limited** resources (for example, a MacBook Pro), you can use [llama.cpp](#quick-start---llamacpp)
|
@@ -427,7 +427,7 @@ Then you can see an output similar to the one below. 🥳
|
|
427 |
### Quick start - Docker
|
428 |
<details>
|
429 |
<summary> Run Yi-34B-chat locally with Docker: a step-by-step guide. ⬇️</summary>
|
430 |
-
<br>This tutorial guides you through every step of running <strong>Yi-34B-Chat on an A800 GPU</strong> locally and then performing inference.
|
431 |
<h4>Step 0: Prerequisites</h4>
|
432 |
<p>Make sure you've installed <a href="https://docs.docker.com/engine/install/?open_in_browser=true">Docker</a> and <a href="https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html">nvidia-container-toolkit</a>.</p>
|
433 |
|
@@ -536,9 +536,10 @@ Now you have successfully asked a question to the Yi model and got an answer!
|
|
536 |
|
537 |
##### Method 2: Perform inference in web
|
538 |
|
539 |
-
1. To initialize a lightweight and swift chatbot,
|
540 |
|
541 |
```bash
|
|
|
542 |
./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf
|
543 |
```
|
544 |
|
@@ -576,12 +577,12 @@ Now you have successfully asked a question to the Yi model and got an answer!
|
|
576 |
|
577 |
2. To access the chatbot interface, open your web browser and enter `http://0.0.0.0:8080` into the address bar.
|
578 |
|
579 |
-
![Yi model chatbot interface - llama.cpp](https://github.com/01-ai/Yi/blob/main/assets/img/yi_llama_cpp1.png)
|
580 |
|
581 |
|
582 |
3. Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer.
|
583 |
|
584 |
-
![Ask a question to Yi model - llama.cpp](https://github.com/01-ai/Yi/blob/main/assets/img/yi_llama_cpp2.png)
|
585 |
|
586 |
</ul>
|
587 |
</details>
|
@@ -602,7 +603,7 @@ python demo/web_demo.py -c <your-model-path>
|
|
602 |
|
603 |
You can access the web UI by entering the address provided in the console into your browser.
|
604 |
|
605 |
-
![Quick start - web demo](https://github.com/01-ai/Yi/blob/main/assets/img/yi_34b_chat_web_demo.gif)
|
606 |
|
607 |
### Finetuning
|
608 |
|
@@ -1010,7 +1011,7 @@ If you're seeking to explore the diverse capabilities within Yi's thriving famil
|
|
1010 |
|
1011 |
Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more.
|
1012 |
|
1013 |
-
![Chat model performance](https://github.com/01-ai/Yi/blob/main/assets/img/
|
1014 |
|
1015 |
<details>
|
1016 |
<summary> Evaluation methods and challenges. ⬇️ </summary>
|
@@ -1027,7 +1028,7 @@ Yi-34B-Chat model demonstrates exceptional performance, ranking first among all
|
|
1027 |
|
1028 |
The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMML, common-sense reasoning, reading comprehension, and more.
|
1029 |
|
1030 |
-
![Base model performance](https://github.com/01-ai/Yi/blob/main/assets/img/benchmark_base.png)
|
1031 |
|
1032 |
<details>
|
1033 |
<summary> Evaluation methods. ⬇️</summary>
|
|
|
82 |
- [Quick start](#quick-start)
|
83 |
- [Choose your path](#choose-your-parth)
|
84 |
- [pip](#pip)
|
85 |
+
- [llama.cpp](#quick-start---llamacpp)
|
86 |
- [Web demo](#web-demo)
|
87 |
- [Fine tune](#fine-tune)
|
88 |
- [Quantization](#quantization)
|
|
|
265 |
- [Quick start](#quick-start)
|
266 |
- [Choose your path](#choose-your-parth)
|
267 |
- [pip](#pip)
|
268 |
+
- [llama.cpp](#quick-start---llamacpp)
|
269 |
- [Web demo](#web-demo)
|
270 |
- [Fine tune](#fine-tune)
|
271 |
- [Quantization](#quantization)
|
272 |
+
- [Deployment](#deployment)
|
273 |
+
- [Learning hub](#learning-hub)
|
274 |
|
275 |
## Quick start
|
276 |
|
|
|
280 |
|
281 |
Select one of the following paths to begin your journey with Yi!
|
282 |
|
283 |
+
![Quick start - Choose your path](https://github.com/01-ai/Yi/blob/main/assets/img/quick_start_path.png?raw=true)
|
284 |
|
285 |
#### 🎯 Deploy Yi locally
|
286 |
|
|
|
288 |
|
289 |
- 🙋♀️ and you have **sufficient** resources (for example, NVIDIA A800 80GB), you can choose one of the following methods:
|
290 |
- [pip](#pip)
|
291 |
+
- [Docker](#quick-start---docker)
|
292 |
- [conda-lock](https://github.com/01-ai/Yi/blob/main/docs/README_legacy.md#12-local-development-environment)
|
293 |
|
294 |
- 🙋♀️ and you have **limited** resources (for example, a MacBook Pro), you can use [llama.cpp](#quick-start---llamacpp)
|
|
|
427 |
### Quick start - Docker
|
428 |
<details>
|
429 |
<summary> Run Yi-34B-chat locally with Docker: a step-by-step guide. ⬇️</summary>
|
430 |
+
<br>This tutorial guides you through every step of running <strong>Yi-34B-Chat on an A800 GPU</strong> or <strong>4*4090</strong> locally and then performing inference.
|
431 |
<h4>Step 0: Prerequisites</h4>
|
432 |
<p>Make sure you've installed <a href="https://docs.docker.com/engine/install/?open_in_browser=true">Docker</a> and <a href="https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html">nvidia-container-toolkit</a>.</p>
|
433 |
|
|
|
536 |
|
537 |
##### Method 2: Perform inference in web
|
538 |
|
539 |
+
1. To initialize a lightweight and swift chatbot, run the following command.
|
540 |
|
541 |
```bash
|
542 |
+
cd llama.cpp
|
543 |
./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf
|
544 |
```
|
545 |
|
|
|
577 |
|
578 |
2. To access the chatbot interface, open your web browser and enter `http://0.0.0.0:8080` into the address bar.
|
579 |
|
580 |
+
![Yi model chatbot interface - llama.cpp](https://github.com/01-ai/Yi/blob/main/assets/img/yi_llama_cpp1.png?raw=true)
|
581 |
|
582 |
|
583 |
3. Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer.
|
584 |
|
585 |
+
![Ask a question to Yi model - llama.cpp](https://github.com/01-ai/Yi/blob/main/assets/img/yi_llama_cpp2.png?raw=true)
|
586 |
|
587 |
</ul>
|
588 |
</details>
|
|
|
603 |
|
604 |
You can access the web UI by entering the address provided in the console into your browser.
|
605 |
|
606 |
+
![Quick start - web demo](https://github.com/01-ai/Yi/blob/main/assets/img/yi_34b_chat_web_demo.gif?raw=true)
|
607 |
|
608 |
### Finetuning
|
609 |
|
|
|
1011 |
|
1012 |
Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more.
|
1013 |
|
1014 |
+
![Chat model performance](https://github.com/01-ai/Yi/blob/main/assets/img/benchmark_chat.png?raw=true)
|
1015 |
|
1016 |
<details>
|
1017 |
<summary> Evaluation methods and challenges. ⬇️ </summary>
|
|
|
1028 |
|
1029 |
The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMML, common-sense reasoning, reading comprehension, and more.
|
1030 |
|
1031 |
+
![Base model performance](https://github.com/01-ai/Yi/blob/main/assets/img/benchmark_base.png?raw=true)
|
1032 |
|
1033 |
<details>
|
1034 |
<summary> Evaluation methods. ⬇️</summary>
|