Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,8 @@ tags:
|
|
| 18 |
- thinking
|
| 19 |
---
|
| 20 |
|
|
|
|
|
|
|
| 21 |
# **Explora-0.6B**
|
| 22 |
|
| 23 |
> **Explora-0.6B** is a lightweight and efficient **general-purpose reasoning model**, fine-tuned on **Qwen3-0.6B** using the first 100,000 entries of the **Open-Omega-Explora-2.5M** dataset. It is tailored for **science and code**-focused reasoning tasks, combining symbolic clarity with fluent instruction-following, ideal for exploratory workflows in STEM domains.
|
|
@@ -99,4 +101,4 @@ print(response)
|
|
| 99 |
* Not optimized for deep multi-hop reasoning or creative tasks
|
| 100 |
* May require prompt engineering for highly specific technical queries
|
| 101 |
* Smaller context window and lower fluency compared to larger models
|
| 102 |
-
* Best used with **specific and scoped questions** for accurate outputs
|
|
|
|
| 18 |
- thinking
|
| 19 |
---
|
| 20 |
|
| 21 |
+
|
| 22 |
+
|
| 23 |
# **Explora-0.6B**
|
| 24 |
|
| 25 |
> **Explora-0.6B** is a lightweight and efficient **general-purpose reasoning model**, fine-tuned on **Qwen3-0.6B** using the first 100,000 entries of the **Open-Omega-Explora-2.5M** dataset. It is tailored for **science and code**-focused reasoning tasks, combining symbolic clarity with fluent instruction-following, ideal for exploratory workflows in STEM domains.
|
|
|
|
| 101 |
* Not optimized for deep multi-hop reasoning or creative tasks
|
| 102 |
* May require prompt engineering for highly specific technical queries
|
| 103 |
* Smaller context window and lower fluency compared to larger models
|
| 104 |
+
* Best used with **specific and scoped questions** for accurate outputs
|