Commit
•
6dbbb82
1
Parent(s):
b472fd8
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,11 @@ Merge of four Solar-10.7B instruct finetunes.
|
|
| 14 |
|
| 15 |
|
| 16 |
## 🌟 Usage
|
|
|
|
| 17 |
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## 🌅 Code Example
|
| 20 |
|
|
@@ -59,7 +63,7 @@ print(generate_response(prompt), "\n")
|
|
| 59 |
|
| 60 |
## Llama.cpp
|
| 61 |
|
| 62 |
-
GGUF Quants available [here]()
|
| 63 |
|
| 64 |
|
| 65 |
|
|
|
|
| 14 |
|
| 15 |
|
| 16 |
## 🌟 Usage
|
| 17 |
+
This SOLAR model _loves_ to code. In my experience, if you ask it a code question it will use almost all of the available token limit to complete the code.
|
| 18 |
|
| 19 |
+
However, this can also be to its own detriment. If the request is complex it may not finish the code in a given time period. This behavior is not because of an eos token, as it finishes sentences quite normally if its a non code question.
|
| 20 |
+
|
| 21 |
+
Your mileage may vary.
|
| 22 |
|
| 23 |
## 🌅 Code Example
|
| 24 |
|
|
|
|
| 63 |
|
| 64 |
## Llama.cpp
|
| 65 |
|
| 66 |
+
GGUF Quants available [here](https://huggingface.co/macadeliccc/Orca-SOLAR-4x10.7b-GGUF)
|
| 67 |
|
| 68 |
|
| 69 |
|