siyoungpark commited on
Commit
473f1f1
·
verified ·
1 Parent(s): 113e7e0

Update README: Remove agentic claims & update API docs

Browse files
Files changed (1) hide show
  1. README.md +1 -5
README.md CHANGED
@@ -18,7 +18,6 @@ tags:
18
 
19
  ## Highlights
20
  * **MoE Architecture (102B / 12B):** Built on a Mixture-of-Experts architecture with **102B total / 12B active parameters**. This design delivers the knowledge depth of a massive model with the inference speed and cost-efficiency of a much smaller model.
21
- * **Agentic Specialist with Parallel Tool Calling:** Engineered to handle complex agentic workflows. It supports **Parallel Tool Calling**, allowing the model to generate multiple function calls in a single turn to execute tasks efficiently.
22
  * **Massive Training Scale:** Pre-trained on **19.7 trillion tokens**, ensuring broad knowledge coverage and robust reasoning capabilities across various domains.
23
 
24
  ## Model Overview
@@ -39,13 +38,10 @@ tags:
39
  ## Quickstart
40
  *Python code snippets and usage examples will be available upon the official release on December 31, 2025.*
41
 
42
- ## Agentic Use & Parallel Tool Calling
43
- Solar Open excels at **Parallel Tool Calling**, enabling the model to request multiple actions simultaneously within a single turn. This reduces latency and improves the efficiency of AI agents.
44
-
45
  ## Public API Access
46
  The official API service for Solar Open is scheduled to launch publicly on **January 1, 2026**.
47
  * **Access:** Upstage Console (Available starting Jan 1, 2026)
48
- * **Documentation:** [**Upstage Console Docs**](https://console.upstage.ai/docs/getting-started)
49
 
50
  ## Citation
51
  If you use Solar Open in your research, please cite:
 
18
 
19
  ## Highlights
20
  * **MoE Architecture (102B / 12B):** Built on a Mixture-of-Experts architecture with **102B total / 12B active parameters**. This design delivers the knowledge depth of a massive model with the inference speed and cost-efficiency of a much smaller model.
 
21
  * **Massive Training Scale:** Pre-trained on **19.7 trillion tokens**, ensuring broad knowledge coverage and robust reasoning capabilities across various domains.
22
 
23
  ## Model Overview
 
38
  ## Quickstart
39
  *Python code snippets and usage examples will be available upon the official release on December 31, 2025.*
40
 
 
 
 
41
  ## Public API Access
42
  The official API service for Solar Open is scheduled to launch publicly on **January 1, 2026**.
43
  * **Access:** Upstage Console (Available starting Jan 1, 2026)
44
+ * **Documentation:** Upstage Console (Available starting Jan 1, 2026)
45
 
46
  ## Citation
47
  If you use Solar Open in your research, please cite: