Locutusque
commited on
Commit
•
7659685
1
Parent(s):
67adc11
Update README.md
Browse files
README.md
CHANGED
@@ -6,5 +6,31 @@ datasets:
|
|
6 |
- Locutusque/InstructMix
|
7 |
language:
|
8 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
-
Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
|
|
|
|
6 |
- Locutusque/InstructMix
|
7 |
language:
|
8 |
- en
|
9 |
+
widget:
|
10 |
+
- text: >-
|
11 |
+
<|USER|> Design a Neo4j database and Cypher function snippet to Display
|
12 |
+
Extreme Dental hygiene: Using Mouthwash for Analysis for Beginners.
|
13 |
+
Implement if/else or switch/case statements to handle different conditions
|
14 |
+
related to the Consent. Provide detailed comments explaining your control
|
15 |
+
flow and the reasoning behind each decision. <|ASSISTANT|>
|
16 |
+
- text: >-
|
17 |
+
<|USER|> Write me a story about a magical place. <|ASSISTANT|>
|
18 |
+
- text: >-
|
19 |
+
<|USER|> Write me an essay about the life of George Washington <|ASSISTANT|>
|
20 |
+
- text: >-
|
21 |
+
<|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|>
|
22 |
+
- text: >-
|
23 |
+
<|USER|> Craft me a list of some nice places to visit around the world. <|ASSISTANT|>
|
24 |
+
- text: >-
|
25 |
+
<|USER|> How to manage a lazy employee: Address the employee verbally. Don't allow an employee's laziness or lack of enthusiasm to become a recurring issue. Tell the employee you're hoping to speak with them about workplace expectations and performance, and schedule a time to sit down together. Question: To manage a lazy employee, it is suggested to talk to the employee. True, False, or Neither? <|ASSISTANT|>
|
26 |
+
inference:
|
27 |
+
parameters:
|
28 |
+
temperature: 0.8
|
29 |
+
do_sample: True
|
30 |
+
top_p: 0.14
|
31 |
+
top_k: 41
|
32 |
+
max_new_tokens: 250
|
33 |
+
repetition_penalty: 1.176
|
34 |
---
|
35 |
+
Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
|
36 |
+
It has so far been trained on approximately 300,000 to 350,000 examples. More epochs are planned for this model.
|