update to new format

README.md

@@ -30,7 +30,7 @@ export HF_HUB_ENABLE_HF_TRANSFER=1
 huggingface-cli download --local-dir CodeLlama-7b-mlx mlx-llama/CodeLlama-7b-mlx
 
 # Run example
-python mlx-examples/llama/llama.py CodeLlama-7b-mlx/CodeLlama-7b.npz CodeLlama-7b-mlx/tokenizer.model "def fibonacci("
+python mlx-examples/llama/llama.py CodeLlama-7b-mlx/ CodeLlama-7b-mlx/tokenizer.model "def fibonacci("
 ```
 
 Please, refer to the [original model card](https://github.com/facebookresearch/codellama/blob/main/MODEL_CARD.md) for details on CodeLlama.

params.json

@@ -0,0 +1,9 @@
+{
+    "dim": 4096,
+    "n_layers": 32,
+    "n_heads": 32,
+    "multiple_of": 256,
+    "ffn_dim_multiplier": 1.0,
+    "norm_eps": 1e-5,
+    "rope_theta": 1000000
+}

CodeLlama-7b.npz → weights.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a9c8c5606a3aec92ddd4320040a02309142cb15916f0480e40c865b817fae1
-size 13477180542
+oid sha256:4b153c305decd738a4486cfabad0e4afbd6ef77b9ee80c62e6b0584ef65e142e
+size 13477181452