pszemraj commited on
Commit
f774aea
1 Parent(s): 8561eb8

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -0
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:`