XeTute commited on
Commit
2317517
·
1 Parent(s): d6c511a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -2
README.md CHANGED
@@ -9,7 +9,7 @@ base_model:
9
 
10
  **Model Training Update**
11
 
12
- We are currently in the process of training our model, with an official release scheduled for **February 22, 2025 at 17:00 according to the timezone of the Islamic Republic of Pakistan.**.
13
 
14
  Introducing **SaplingDream**, a compact GPT model with 0.5 billion parameters, based on the [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) architecture. This model has been fine-tuned on reasoning datasets with meticulous attention to detail, ensuring the highest quality—hence the name "SaplingDream." See this as advanced "instruction" tuning for the base model to support reasoning to make up for its size efficiently.
15
 
@@ -17,4 +17,12 @@ To enhance generalization, we are fine-tuning the base model using Stochastic Gr
17
 
18
  For training, we are utilizing the [open-thoughts/OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k) and [prithivMLmods/Deepthink-Reasoning-Ins](https://huggingface.co/datasets/prithivMLmods/Deepthink-Reasoning-Ins) datasets across the entire epoch.
19
 
20
- **Stay tuned! Until training is complete, we will be uploading every (last three) 200th checkpoint from a total of 14,275 optimization steps. Check out the `Files and versions` section for updates!**
 
 
 
 
 
 
 
 
 
9
 
10
  **Model Training Update**
11
 
12
+ We are currently in the process of training our model, with an official release scheduled for **February 22, 2025 at 17:00 according to the timezone of the Islamic Republic of Pakistan**.
13
 
14
  Introducing **SaplingDream**, a compact GPT model with 0.5 billion parameters, based on the [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) architecture. This model has been fine-tuned on reasoning datasets with meticulous attention to detail, ensuring the highest quality—hence the name "SaplingDream." See this as advanced "instruction" tuning for the base model to support reasoning to make up for its size efficiently.
15
 
 
17
 
18
  For training, we are utilizing the [open-thoughts/OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k) and [prithivMLmods/Deepthink-Reasoning-Ins](https://huggingface.co/datasets/prithivMLmods/Deepthink-Reasoning-Ins) datasets across the entire epoch.
19
 
20
+ **Stay tuned! Until training is complete, we will be uploading every (last three) 200th checkpoint from a total of 14,275 optimization steps. Check out the `Files and versions` section for updates!**
21
+
22
+ ---
23
+ [Chat with our Assistant](https://xetute.com/)
24
+
25
+ ---
26
+
27
+ Long live the Islamic Republic of Pakistan; Glory to the Islamic Republic of Pakistan 🇵🇰
28
+ ![The Flag of the Islamic Federal Republic of Pakistan](https://upload.wikimedia.org/wikipedia/commons/3/32/Flag_of_Pakistan.svg)