mlx-community
/

Virtuoso-Small-4bit

4-bit precision

Model card Files Files and versions Community

Felladrin commited on Dec 11, 2024

Commit

6b4cf1c

·

verified ·

1 Parent(s): a655f40

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -100,9 +100,9 @@ model-index:
       name: Open LLM Leaderboard
 ---
-# Felladrin/Virtuoso-Small-Q4-mlx
-The Model [Felladrin/Virtuoso-Small-Q4-mlx](https://huggingface.co/Felladrin/Virtuoso-Small-Q4-mlx) was converted to MLX format from [arcee-ai/Virtuoso-Small](https://huggingface.co/arcee-ai/Virtuoso-Small) using mlx-lm version **0.19.2**.
 ## Use with mlx
@@ -113,7 +113,7 @@ pip install mlx-lm
 ```python
 from mlx_lm import load, generate
-model, tokenizer = load("Felladrin/Virtuoso-Small-Q4-mlx")
 prompt="hello"

       name: Open LLM Leaderboard
 ---
+# mlx-community/Virtuoso-Small-4bit
+The Model [mlx-community/Virtuoso-Small-4bit](https://huggingface.co/mlx-community/Virtuoso-Small-4bit) was converted to MLX format from [arcee-ai/Virtuoso-Small](https://huggingface.co/arcee-ai/Virtuoso-Small) using mlx-lm version **0.19.2**.
 ## Use with mlx
 ```python
 from mlx_lm import load, generate
+model, tokenizer = load("mlx-community/Virtuoso-Small-4bit")
 prompt="hello"