Update README.md
Browse files
README.md
CHANGED
|
@@ -36,7 +36,7 @@ The ultimate goal is to create a "more expressive" 3B-level model, making it mor
|
|
| 36 |
|
| 37 |
This repository provides LoRA adapters and GGUF quantized versions for flexible deployment across various hardware environments.
|
| 38 |
|
| 39 |
-
**
|
| 40 |
|
| 41 |
---
|
| 42 |
|
|
@@ -168,6 +168,8 @@ Therefore, the improvements brought about by fine-tuning are incremental and **d
|
|
| 168 |
|
| 169 |
该仓库提供了 LoRA 适配器及 GGUF 量化版本，便于在各种硬件环境中灵活部署。
|
| 170 |
|
|
|
|
|
|
|
| 171 |
---
|
| 172 |
|
| 173 |
## 模型提升与优势 (Model Enhancements and Strengths)
|
|
|
|
| 36 |
|
| 37 |
This repository provides LoRA adapters and GGUF quantized versions for flexible deployment across various hardware environments.
|
| 38 |
|
| 39 |
+
**✨Jackrong/Soren-Logos-3B** is a **GRPO-trained** version of **Soren-Oracle-Chat-3B** produced after a set number of optimization steps.
|
| 40 |
|
| 41 |
---
|
| 42 |
|
|
|
|
| 168 |
|
| 169 |
该仓库提供了 LoRA 适配器及 GGUF 量化版本，便于在各种硬件环境中灵活部署。
|
| 170 |
|
| 171 |
+
**✨Jackrong/Soren-Logos-3B**是**Soren-Oracle-Chat-3B**经过一定步数的**GRPO**的模型。
|
| 172 |
+
|
| 173 |
---
|
| 174 |
|
| 175 |
## 模型提升与优势 (Model Enhancements and Strengths)
|