Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Llama3-ThinkQ8
|
| 2 |
|
| 3 |
A fine-tuned version of Llama 3 that shows explicit thinking using `<think>` and `<answer>` tags. This model is quantized to 4-bit (Q4) for efficient inference.
|
|
@@ -49,4 +69,4 @@ Using each number in this tensor ONLY once (5, 8, 3) and any arithmetic operatio
|
|
| 49 |
|
| 50 |
```
|
| 51 |
Explain the concept of quantum entanglement to a high school student.
|
| 52 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- Jiayi-Pan/Countdown-Tasks-3to4
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
- es
|
| 8 |
+
- ar
|
| 9 |
+
- la
|
| 10 |
+
base_model:
|
| 11 |
+
- unsloth/Llama-3.2-3B-Instruct
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
+
library_name: transformers
|
| 14 |
+
tags:
|
| 15 |
+
- unsloth
|
| 16 |
+
- llama
|
| 17 |
+
- deepseek
|
| 18 |
+
- GGUF
|
| 19 |
+
- Q4_K_M
|
| 20 |
+
---
|
| 21 |
# Llama3-ThinkQ8
|
| 22 |
|
| 23 |
A fine-tuned version of Llama 3 that shows explicit thinking using `<think>` and `<answer>` tags. This model is quantized to 4-bit (Q4) for efficient inference.
|
|
|
|
| 69 |
|
| 70 |
```
|
| 71 |
Explain the concept of quantum entanglement to a high school student.
|
| 72 |
+
```
|