Update README.md
Browse files
README.md
CHANGED
@@ -20,8 +20,8 @@ Other experimental models, based off `creative-writer-v0.1-alfa-35b` that attemp
|
|
20 |
# Usage
|
21 |
|
22 |
- Use the normal `command-r` chat template: `'<|START_OF_TURN_TOKEN|><|USER_TOKEN|>prompt<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>reply...'`.
|
23 |
-
- I suggest using **no system prompt** with this (and all other `Cohere` models!), as it writes *much* better without IMO...
|
24 |
-
- You **
|
25 |
|
26 |
---
|
27 |
|
|
|
20 |
# Usage
|
21 |
|
22 |
- Use the normal `command-r` chat template: `'<|START_OF_TURN_TOKEN|><|USER_TOKEN|>prompt<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>reply...'`.
|
23 |
+
- I suggest using **no system prompt** with this (and all other `Cohere` models!), as it writes *much* better without it IMO...
|
24 |
+
- You ***MUST*** **use some (small) value of min-p** with this such as `0.01`(and with the original `c4ai-command-r-v01` model), **or else the model will output gibberish!**
|
25 |
|
26 |
---
|
27 |
|