bc897484fe2de30f296dfacad584f3a7b3e54f0e860e5fccfc8a0b7215642300

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -17,7 +17,7 @@ fine-tuning: false
 
 # mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit
 
-The Model [mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit](https://huggingface.co/mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit) was converted to MLX format from [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) using mlx-lm version **0.19.1**.
+The Model [mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit](https://huggingface.co/mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-8bit) was converted to MLX format from [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) using mlx-lm version **0.19.0**.
 
 ## Use with mlx
 

model-00015-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03289dccbc9d3ec33db8a8ed28fbbcebd9f63f1bdbebdfb4a5077617b77cf0d0
-size 1865074261
+oid sha256:8f35474696a9f25d677ee265b38ebe24a30e021beed1e3f3956f32e3e25234e8
+size 1865074267