Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,26 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
tags:
|
| 4 |
-
- unsloth
|
| 5 |
-
- trl
|
| 6 |
-
- sft
|
| 7 |
-
- deepseek-r1-distill-llama-8b
|
| 8 |
-
datasets:
|
| 9 |
-
- FreedomIntelligence/medical-o1-reasoning-SFT
|
| 10 |
-
base_model:
|
| 11 |
-
- unsloth/DeepSeek-R1-Distill-Llama-8B
|
| 12 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- unsloth
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- deepseek-r1-distill-llama-8b
|
| 8 |
+
datasets:
|
| 9 |
+
- FreedomIntelligence/medical-o1-reasoning-SFT
|
| 10 |
+
base_model:
|
| 11 |
+
- unsloth/DeepSeek-R1-Distill-Llama-8B
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
Model was trained on the first 500 rows of the dataset with RunPod Pytorch 2.4.0, GPU A40 (48 GB VRAM, 50GB RAM 9vCPU).
|
| 15 |
+
Duration: 11m 38s
|
| 16 |
+
|
| 17 |
+
From W&B
|
| 18 |
+
OS Linux-6.8.0-49-generic-x86_64-with-glibc2.35
|
| 19 |
+
Python version CPython 3.11.10
|
| 20 |
+
|
| 21 |
+
System Hardware
|
| 22 |
+
CPU count 48
|
| 23 |
+
Logical CPU count 96
|
| 24 |
+
GPU count 1
|
| 25 |
+
GPU type NVIDIA A40
|
| 26 |
+
|