Pankaj Mathur
commited on
Commit
·
8889e72
1
Parent(s):
74d1fbd
Update README.md
Browse files
README.md
CHANGED
|
@@ -77,4 +77,11 @@ output = rest[0][length:]
|
|
| 77 |
string = tokenizer.decode(output, skip_special_tokens=True)
|
| 78 |
print(f'[!] Response: {string}')
|
| 79 |
|
| 80 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
string = tokenizer.decode(output, skip_special_tokens=True)
|
| 78 |
print(f'[!] Response: {string}')
|
| 79 |
|
| 80 |
+
```
|
| 81 |
+
|
| 82 |
+
Next Goals:
|
| 83 |
+
1) Try more data, Dolly V2, WizardLM, & Others (we are open for suggestions)
|
| 84 |
+
2) Try bigger OpenLLaMA models 7B and 13B
|
| 85 |
+
3) Try better GPU for training, couldn't get 8xA100 (40GB), I guess they are in hot demand now.
|
| 86 |
+
4) Provide more options for Text generation UI. (may be https://github.com/oobabooga/text-generation-webui)
|
| 87 |
+
6) Provide 4bit quantized model (may be TheBloke can help here)
|