Update README.md
Browse files
README.md
CHANGED
@@ -7,5 +7,5 @@ license: other
|
|
7 |
This is a [ggml](https://github.com/ggerganov/ggml/) quantized version of [Replit-v2-CodeInstruct-3B](https://huggingface.co/teknium/Replit-v2-CodeInstruct-3B). Quantized to 4bit -> q4_1.
|
8 |
To run inference you can use ggml directly or [ctransformers](https://github.com/marella/ctransformers).
|
9 |
|
10 |
-
Memory usage of model: **2GB~**
|
11 |
-
Repo to run the model using ctransformers: https://github.com/abacaj/replit-3B-inference
|
|
|
7 |
This is a [ggml](https://github.com/ggerganov/ggml/) quantized version of [Replit-v2-CodeInstruct-3B](https://huggingface.co/teknium/Replit-v2-CodeInstruct-3B). Quantized to 4bit -> q4_1.
|
8 |
To run inference you can use ggml directly or [ctransformers](https://github.com/marella/ctransformers).
|
9 |
|
10 |
+
- Memory usage of model: **2GB~**
|
11 |
+
- Repo to run the model using ctransformers: https://github.com/abacaj/replit-3B-inference
|