nightmedia
/

granite-3.3-8b-instruct-dwq6-mlx

Text Generation

Model card Files Files and versions

nightmedia commited on Jul 14

Commit

a70d2df

·

verified ·

1 Parent(s): 4e30d6d

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -12,6 +12,8 @@ base_model: ibm-granite/granite-3.3-8b-instruct
 # granite-3.3-8b-instruct-dwq6-mlx
 This model [granite-3.3-8b-instruct-dwq6-mlx](https://huggingface.co/granite-3.3-8b-instruct-dwq6-mlx) was
 converted to MLX format from [ibm-granite/granite-3.3-8b-instruct](https://huggingface.co/ibm-granite/granite-3.3-8b-instruct)
 using mlx-lm version **0.26.0**.

 # granite-3.3-8b-instruct-dwq6-mlx
+Trained on 66 samples, group_size 32, last avg loss 0.1463, final loss 0.0813
 This model [granite-3.3-8b-instruct-dwq6-mlx](https://huggingface.co/granite-3.3-8b-instruct-dwq6-mlx) was
 converted to MLX format from [ibm-granite/granite-3.3-8b-instruct](https://huggingface.co/ibm-granite/granite-3.3-8b-instruct)
 using mlx-lm version **0.26.0**.