Auto Sync from git://github.com/01-ai/Yi.git/commit/e3e47d27d65641181e2aeb600304181dd2a7230a

This commit is contained in:
ai-modelscope
2024-03-22 20:09:08 +08:00
parent a850b459d1
commit 1ac65fa520

View File

@@ -860,7 +860,7 @@ python quantization/gptq/eval_quantized_model.py \
--trust_remote_code --trust_remote_code
``` ```
<details style="display: inline;"><summary>For a more detailed explanation, see the explanations below. ⬇️</summary> <ul> <details style="display: inline;"><summary>For details, see the explanations below. ⬇️</summary> <ul>
#### GPT-Q quantization #### GPT-Q quantization
@@ -885,7 +885,6 @@ python quant_autogptq.py --model /base_model \
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
``` ```
##### Run Quantized Model ##### Run Quantized Model
You can run a quantized model using the `eval_quantized_model.py`: You can run a quantized model using the `eval_quantized_model.py`:
@@ -897,6 +896,7 @@ python eval_quantized_model.py --model /quantized_model --trust_remote_code
</details> </details>
#### AWQ #### AWQ
```bash ```bash
python quantization/awq/quant_autoawq.py \ python quantization/awq/quant_autoawq.py \
--model /base_model \ --model /base_model \
@@ -1017,7 +1017,9 @@ At the same time, we also warmly invite you to join our collaborative effort by
With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳 With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
#### Tutorials #### Tutorials
##### English tutorials ##### English tutorials
| Type | Deliverable | Date | Author | | Type | Deliverable | Date | Author |
|-------------|--------------------------------------------------------|----------------|----------------| |-------------|--------------------------------------------------------|----------------|----------------|
| Video | [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) | | Video | [Run dolphin-2.2-yi-34b on IoT Devices](https://www.youtube.com/watch?v=NJ89T5mO25Y) | 2023-11-30 | [Second State](https://github.com/second-state) |
@@ -1025,8 +1027,8 @@ With all these resources at your fingertips, you're ready to start your exciting
| Video | [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) | | Video | [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05 | [Fahd Mirza](https://www.youtube.com/@fahdmirza) |
| Video | [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) | | Video | [Dolphin Yi 34b - Brand New Foundational Model TESTED](https://www.youtube.com/watch?v=On3Zuv27V3k&t=85s) | 2023-11-27 | [Matthew Berman](https://www.youtube.com/@matthew_berman) |
##### Chinese tutorials ##### Chinese tutorials
| Type | Deliverable | Date | Author | | Type | Deliverable | Date | Author |
|-------------|--------------------------------------------------------|----------------|----------------| |-------------|--------------------------------------------------------|----------------|----------------|
| Blog | [实测零一万物Yi-VL多模态语言模型能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) | | Blog | [实测零一万物Yi-VL多模态语言模型能准确“识图吃瓜”](https://mp.weixin.qq.com/s/fu4O9XvJ03JhimsEyI-SsQ) | 2024-02-02 | [苏洋](https://github.com/soulteary) |
@@ -1160,8 +1162,8 @@ For detailed capabilities of the Yi series model, see [Yi: Open Foundation Model
## Benchmarks ## Benchmarks
- [Chat model performance](#-chat-model-performance) - [Chat model performance](#chat-model-performance)
- [Base model performance](#-base-model-performance) - [Base model performance](#base-model-performance)
### Chat model performance ### Chat model performance