Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- teknium/openhermes
|
5 |
+
inference:
|
6 |
+
parameters:
|
7 |
+
do_sample: true
|
8 |
+
renormalize_logits: true
|
9 |
+
temperature: 0.25
|
10 |
+
top_p: 0.95
|
11 |
+
top_k: 50
|
12 |
+
min_new_tokens: 2
|
13 |
+
max_new_tokens: 96
|
14 |
+
repetition_penalty: 1.1
|
15 |
+
no_repeat_ngram_size: 6
|
16 |
+
epsilon_cutoff: 0.0006
|
17 |
+
widget:
|
18 |
+
- text: >
|
19 |
+
Below is an instruction that describes a task, paired with an input that
|
20 |
+
provides further context. Write a response that appropriately completes
|
21 |
+
the request.
|
22 |
+
|
23 |
+
### Instruction:
|
24 |
+
|
25 |
+
Write an ode to Chipotle burritos.
|
26 |
+
|
27 |
+
### Response:
|
28 |
+
example_title: burritos
|
29 |
+
---
|
30 |
+
|
31 |
+
|
32 |
+
# BEE-spoke-data/smol_llama-220M-openhermes
|
33 |
+
|
34 |
+
|
35 |
+
prompt format is alpaca
|
36 |
+
|
37 |
+
|
38 |
+
```
|
39 |
+
Below is an instruction that describes a task, paired with an input that
|
40 |
+
provides further context. Write a response that appropriately completes
|
41 |
+
the request.
|
42 |
+
|
43 |
+
### Instruction:
|
44 |
+
|
45 |
+
How can I increase my meme production/output? Currently, I only create them in ancient babylonian which is time consuming.
|
46 |
+
|
47 |
+
### Inputs:
|
48 |
+
|
49 |
+
### Response:
|
50 |
+
```
|
51 |
+
|
52 |
+
It was trained on inputs so if you have inputs (like some text to ask a question about) then include it under `### Inputs:`
|