update to new format

README.md

@@ -29,7 +29,7 @@ export HF_HUB_ENABLE_HF_TRANSFER=1
 huggingface-cli download --local-dir CodeLlama-7b-Python-mlx mlx-llama/CodeLlama-7b-Python-mlx
 
 # Run example
-python mlx-examples/llama/llama.py CodeLlama-7b-Python-mlx/CodeLlama-7b-Python.npz CodeLlama-7b-Python-mlx/tokenizer.model "def fibonacci("
+python mlx-examples/llama/llama.py CodeLlama-7b-Python-mlx/ CodeLlama-7b-Python-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-Python.npz → weights.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936ea09ef86a484954c0f2dc1447ec89d446c5097a4c65986f7432611e1c701d
-size 13476918398
+oid sha256:a63f8288d2e0a6f5140169662eb3d27af8d9829ec3b4d8d186427b2ed26717e5
+size 13476919308