Locutusque
commited on
Commit
•
11130c4
1
Parent(s):
17c5f03
Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,31 @@ datasets:
|
|
5 |
language:
|
6 |
- en
|
7 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
# LocutusqueXFelladrin-TinyMistral248M-Instruct
|
10 |
This model was created by merging Locutusque/TinyMistral-248M-Instruct and Felladrin/TinyMistral-248M-SFT-v4 using mergekit. After the two models were merged, the resulting model was further trained on ~20,000 examples on the Locutusque/inst_mix_v2_top_100k at a low learning rate to further normalize weights. The following is the YAML config used to merge:
|
|
|
5 |
language:
|
6 |
- en
|
7 |
pipeline_tag: text-generation
|
8 |
+
widget:
|
9 |
+
- text: >-
|
10 |
+
<|USER|> Design a Neo4j database and Cypher function snippet to Display
|
11 |
+
Extreme Dental hygiene: Using Mouthwash for Analysis for Beginners.
|
12 |
+
Implement if/else or switch/case statements to handle different conditions
|
13 |
+
related to the Consent. Provide detailed comments explaining your control
|
14 |
+
flow and the reasoning behind each decision. <|ASSISTANT|>
|
15 |
+
- text: >-
|
16 |
+
<|USER|> Write me a story about a magical place. <|ASSISTANT|>
|
17 |
+
- text: >-
|
18 |
+
<|USER|> Write me an essay about the life of George Washington <|ASSISTANT|>
|
19 |
+
- text: >-
|
20 |
+
<|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|>
|
21 |
+
- text: >-
|
22 |
+
<|USER|> Craft me a list of some nice places to visit around the world. <|ASSISTANT|>
|
23 |
+
- text: >-
|
24 |
+
<|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|>
|
25 |
+
inference:
|
26 |
+
parameters:
|
27 |
+
temperature: 0.4
|
28 |
+
do_sample: True
|
29 |
+
top_p: 0.34
|
30 |
+
top_k: 30
|
31 |
+
max_new_tokens: 250
|
32 |
+
repetition_penalty: 1.15
|
33 |
---
|
34 |
# LocutusqueXFelladrin-TinyMistral248M-Instruct
|
35 |
This model was created by merging Locutusque/TinyMistral-248M-Instruct and Felladrin/TinyMistral-248M-SFT-v4 using mergekit. After the two models were merged, the resulting model was further trained on ~20,000 examples on the Locutusque/inst_mix_v2_top_100k at a low learning rate to further normalize weights. The following is the YAML config used to merge:
|