deepseekmirror/DeepSeek-LLM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-LLM.git synced 2025-02-23 06:09:06 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Freja 2023-11-30 09:01:20 +08:00
parent 2c03108033
commit 7f842fdc0d
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -68,7 +68,6 @@ Introducing DeepSeek LLM, an advanced language model comprising 67 billion param
- **Mastery in Chinese Language:** Based on our evaluation, DeepSeek LLM 67B Chat surpasses GPT-3.5 in Chinese. - **Mastery in Chinese Language:** Based on our evaluation, DeepSeek LLM 67B Chat surpasses GPT-3.5 in Chinese.
<a id="model-downloads"></a>
## 2. Model Downloads ## 2. Model Downloads
We release the DeepSeek LLM 7B/67B, including both base and chat models, to the public. To support a broader and more diverse range of research within both academic and commercial communities, we are providing access to the intermediate checkpoints of the base model from its training process. Please **note** that the use of this model is subject to the terms outlined in [License section](#8-license). Commercial usage is permitted under these terms. We release the DeepSeek LLM 7B/67B, including both base and chat models, to the public. To support a broader and more diverse range of research within both academic and commercial communities, we are providing access to the intermediate checkpoints of the base model from its training process. Please **note** that the use of this model is subject to the terms outlined in [License section](#8-license). Commercial usage is permitted under these terms.
@ -96,7 +95,6 @@ aws s3 cp s3://deepseek-ai/DeepSeek-LLM/DeepSeek-LLM-7B-Base <local_path> --recu
aws s3 cp s3://deepseek-ai/DeepSeek-LLM/DeepSeek-LLM-67B-Base <local_path> --recursive --request-payer aws s3 cp s3://deepseek-ai/DeepSeek-LLM/DeepSeek-LLM-67B-Base <local_path> --recursive --request-payer
``` ```
<a id="evaluation-results"></a>
## 3. Evaluation Results ## 3. Evaluation Results
### Base Model ### Base Model
@ -204,7 +202,6 @@ We release the training loss curve and several benchmark metrics curves, as deta
<img src="images/pretrain_metric.png" alt="result" width="80%"> <img src="images/pretrain_metric.png" alt="result" width="80%">
</div> </div>
<a id="quick-start"></a>
## 5. Quick Start ## 5. Quick Start
### Installation ### Installation