Commit
•
f9fe2ae
1
Parent(s):
059e60b
Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,16 @@ tags:
|
|
12 |
- not-for-all-audiences
|
13 |
- merge
|
14 |
- code
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
---
|
16 |
# Model description
|
17 |
Fine-tuned Locutusque/TinyMistral-248m-v2.5 on SlimOrca-Dedup and Hercules-v1.0. Averaged a loss of 1.5 during training. This model's performance is excellent considering it's size.
|
|
|
12 |
- not-for-all-audiences
|
13 |
- merge
|
14 |
- code
|
15 |
+
inference:
|
16 |
+
parameters:
|
17 |
+
do_sample: true
|
18 |
+
temperature: 0.2
|
19 |
+
top_p: 0.14
|
20 |
+
top_k: 12
|
21 |
+
max_new_tokens: 250
|
22 |
+
repetition_penalty: 1.15
|
23 |
+
widget:
|
24 |
+
- text: "<|im_start|>user\nWrite me a Python program that calculates the factorial of n. <|im_end|>\n<|im_start|>assistant\n"
|
25 |
---
|
26 |
# Model description
|
27 |
Fine-tuned Locutusque/TinyMistral-248m-v2.5 on SlimOrca-Dedup and Hercules-v1.0. Averaged a loss of 1.5 during training. This model's performance is excellent considering it's size.
|