Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ Quantized to FP16 and released under the [Apache-2.0](https://choosealicense.com
|
|
16 |
Compute generously provided by [Higgsfield AI](https://higgsfield.ai/model/655559e6b5777dab620095e0).
|
17 |
|
18 |
|
19 |
-
Prompt format: Alpaca
|
20 |
```
|
21 |
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
22 |
|
@@ -26,4 +26,10 @@ Below is an instruction that describes a task. Write a response that appropriate
|
|
26 |
### Response:
|
27 |
```
|
28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
\*as of 21 Nov 2023. "commercially-usable" includes both an open-source base model and a *non-synthetic* open-source finetune dataset. updated leaderboard results available [here](https://huggingfaceh4-open-llm-leaderboard.hf.space).
|
|
|
16 |
Compute generously provided by [Higgsfield AI](https://higgsfield.ai/model/655559e6b5777dab620095e0).
|
17 |
|
18 |
|
19 |
+
## Prompt format: Alpaca
|
20 |
```
|
21 |
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
22 |
|
|
|
26 |
### Response:
|
27 |
```
|
28 |
|
29 |
+
## Recommended preset:
|
30 |
+
- temperature: 0.2
|
31 |
+
- top_k: 50
|
32 |
+
- top_p 0.95
|
33 |
+
- repetition_penalty: 1.1
|
34 |
+
|
35 |
\*as of 21 Nov 2023. "commercially-usable" includes both an open-source base model and a *non-synthetic* open-source finetune dataset. updated leaderboard results available [here](https://huggingfaceh4-open-llm-leaderboard.hf.space).
|