Views
No views yet
1merge_method: task_swapping
2base_model: Doctor-Shotgun/TinyLlama-1.1B-32k
3models:
4 - model: cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser
5 parameters:
6 weight: 0.75
7 diagonal_offset: 5
8 - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
9 parameters:
10 weight: 0.85
11 diagonal_offset: 17
12 invert_offset: True
13dtype: bfloat16
14name: bye
15---
16merge_method: task_swapping
17base_model: Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct
18models:
19 - model: vihangd/DopeyTinyLlama-1.1B-v1
20 parameters:
21 weight: 0.8
22 diagonal_offset: 3
23 invert_offset: False
24dtype: bfloat16
25name: hello
26---
27merge_method: task_arithmetic
28base_model: Doctor-Shotgun/TinyLlama-1.1B-32k
29models:
30 - model: hello
31 parameters:
32 weight: 0.66
33 - model: bye+Anarchist/PIPPA_LORA_TinyLlama
34 parameters:
35 weight: 0.5
36dtype: bfloat16| Metric | Value |
|---|---|
| Avg. | 32.99 |
| AI2 Reasoning Challenge (25-Shot) | 31.48 |
| HellaSwag (10-Shot) | 48.39 |
| MMLU (5-Shot) | 25.05 |
| TruthfulQA (0-shot) | 33.45 |
| Winogrande (5-shot) | 58.48 |
| GSM8k (5-shot) | 1.06 |