Commit
•
7fbd7b5
1
Parent(s):
9f715a9
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gpl-3.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
- ja
|
| 7 |
+
- de
|
| 8 |
+
---
|
| 9 |
+
Tokenizer is different from cohere - and chat template is ChatML - fully fine-tuned at 128K+ ~ 30M entries long, web crawl input, GPT-4-32k/3.5-16k output, synthetic dataset - 1 epoch
|
| 10 |
+
|
| 11 |
+
For another candidate version of 1 epoch - https://huggingface.co/CausalLM/35b-beta - somehow less overfitting?
|
| 12 |
+
|
| 13 |
+
No loras, no quants, no tricks.
|
| 14 |
+
|
| 15 |
+
This one is not "very 128k", use https://huggingface.co/CausalLM/35b-beta-long for long context. But better in general tasks, knowledge, coding and so on.
|
| 16 |
+
|
| 17 |
+
And, merge them if you want!
|