Update README.md
Browse files
README.md
CHANGED
|
@@ -14,15 +14,15 @@ language:
|
|
| 14 |
- en
|
| 15 |
---
|
| 16 |
|
| 17 |
-
#
|
| 18 |
|
| 19 |
-
- **Developed by:**
|
| 20 |
- **License:** apache-2.0
|
| 21 |
- **Fine-tuned from:** Qwen/Qwen2.5-3B-Instruct
|
| 22 |
- **GGUF Format:** 4-bit quantized (Q4) for optimized inference
|
| 23 |
|
| 24 |
## **Model Description**
|
| 25 |
-
|
| 26 |
|
| 27 |
Trained using **GRPO (General Reinforcement with Policy Optimization)**, the model excels in **self-reasoning, logical deduction, and structured problem-solving**, comparable to **DeepSeek-R1**. The **Q4 quantization** ensures significantly lower memory requirements while maintaining strong reasoning performance.
|
| 28 |
|
|
@@ -43,7 +43,7 @@ Trained using **GRPO (General Reinforcement with Policy Optimization)**, the mod
|
|
| 43 |
# Use this prompt for more detailed and personalized results. This is the recommended prompt as the model was tuned on it.
|
| 44 |
|
| 45 |
```python
|
| 46 |
-
You are a reasoning model made by researcher at
|
| 47 |
|
| 48 |
<reasoning>
|
| 49 |
...
|
|
@@ -64,7 +64,4 @@ Respond in the following format:
|
|
| 64 |
<answer>
|
| 65 |
...
|
| 66 |
</answer>
|
| 67 |
-
"""
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
|
|
|
| 14 |
- en
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# TBH.AI Base Reasoning (GGUF - Q4)
|
| 18 |
|
| 19 |
+
- **Developed by:** TBH.AI
|
| 20 |
- **License:** apache-2.0
|
| 21 |
- **Fine-tuned from:** Qwen/Qwen2.5-3B-Instruct
|
| 22 |
- **GGUF Format:** 4-bit quantized (Q4) for optimized inference
|
| 23 |
|
| 24 |
## **Model Description**
|
| 25 |
+
TBH.AI Base Reasoning (GGUF - Q4) is a **4-bit GGUF quantized** version of `saishshinde15/TBH.AI_Base_Reasoning`, a fine-tuned model based on **Qwen 2.5**. This version is designed for **high-efficiency inference on CPU/GPU with minimal memory usage**, making it ideal for on-device applications and low-latency AI systems.
|
| 26 |
|
| 27 |
Trained using **GRPO (General Reinforcement with Policy Optimization)**, the model excels in **self-reasoning, logical deduction, and structured problem-solving**, comparable to **DeepSeek-R1**. The **Q4 quantization** ensures significantly lower memory requirements while maintaining strong reasoning performance.
|
| 28 |
|
|
|
|
| 43 |
# Use this prompt for more detailed and personalized results. This is the recommended prompt as the model was tuned on it.
|
| 44 |
|
| 45 |
```python
|
| 46 |
+
You are a reasoning model made by researcher at TBH.AI and your role is to respond in the following format only and in detail :
|
| 47 |
|
| 48 |
<reasoning>
|
| 49 |
...
|
|
|
|
| 64 |
<answer>
|
| 65 |
...
|
| 66 |
</answer>
|
| 67 |
+
"""
|
|
|
|
|
|
|
|
|